The Broad Institute (Cambridge, MA) and the Department of Electrical Engineering and Computer Science (EECS) at the Massachusetts Institute of Technology (Cambridge, Massachusetts) seek applicants for a tenure-track position at the Assistant or un-tenured Associate Professor level, effective July 1, 2023, or as soon as possible thereafter. Rank will be determined based on qualifications and experience.

We welcome outstanding applicants with research and teaching interests in any area of machine learning, artificial intelligence and/or statistics that could drive the frontier of biomedical research at any scale (proteins, cells, tissues or organisms). The successful candidate will be a faculty member in the Department of EECS at MIT and a Broad Core Institute Member.

We believe that the intellectual, cultural and social diversity of our faculty, staff, and students is vitally important to the distinction and excellence of our academic and research programs. We seek candidates who support our institutional commitment to ensuring that the Broad Institute and MIT are inclusive, equitable, and diverse.

Successful applicants are expected to share our commitment to undergraduate and graduate education by teaching courses and supervising graduate and undergraduate research, as well as develop and lead a vibrant, independent research program that would benefit from being in the Broad Institute environment.

Candidates are expected to have had formal graduate training and research focus in the computational sciences (e.g., as evidenced by their publication record), and hold a PhD (or equivalent terminal degree) in the field of computer or mathematical sciences, engineering (biological, chemical, etc.), or a related field by the start of employment.

Complete applications should be received by January 1, 2023. Applications include a cover letter, curriculum vitae, research statement (2-4 pages), and teaching statement (1-2 pages). In addition, candidates should provide a statement on diversity, inclusion, and belonging, including past and current contributions as well as their vision and plans for the future in these areas (1-2 pages). Application materials should be submitted to https://faculty-searches.mit.edu/bree/register.tcl.

Completed application review will begin after January 1, 2023.

MIT and Broad are equal employment opportunity employers. All qualified applicants will receive consideration for employment and will not be discriminated against on the basis of race, color, sex, sexual orientation, gender identity, religion, disability, age, genetic information, veteran status, ancestry, or national or ethnic origin.

Thee “Learning Meaningful Representation of Life” group (PI Paul Villoutreix) of the Turing Center for Living Systems and the “Networks and Systems Biology” group (PI Anaïs Baudot) of the Marseille Medical Genetics Institute in Marseille have an open position for a

Project: Biological processes are now being assessed at different levels, from genomics, to epigenomics, transcriptomics, metabolomics or proteomics. This data yields unprecedented opportunities to better understand biological systems in healthy and pathological states. Designing theoretical and computational approaches for the joint analysis of multi-omics datasets is currently one of the most relevant and challenging questions in computational biology. With rare diseases however, the task is staggering. It is estimated that about 300 million patients suffer from 5 000 to 8 000 rare genetic diseases worldwide, however, the access to patient samples is by definition limited. Our main objective in the CAMUDI project is to develop innovative approaches for multimodal data integration that can deal with a small number of samples.With this project we will explore artificial neural networks and multimodal autoencoders with transfer learning to integrate omics with images data. We will focus in particular on Facio Scapulo Humeral Dystrophy (FSHD), which is a peculiar form of muscular dystrophy with predominant weaknesses of specific muscles of the face and upper body.

Environment: The successful candidate will work in an interdisciplinary environment composed of mathematicians and computer scientists (https://bioml.lis-lab.fr - Villoutreix team) and bioinformaticians (https://www.marseille-medical-genetics.org/a-baudot/ - Baudot team). Moreover, the candidate will benefit from the vibrant environment of the Turing Center for Living Systems (https://centuri-livingsystems.org), and will be involved in the machine learning department of the Computer Science Lab (https://qarma.lis-lab.fr).

Qualifications:

PhD in Bioinformatics, Computational Biology, Mathematical Biology, Computer Science, Applied Mathematics or related fields

Experience in the development and application of Machine Learning methods

Experience with -omics data

A previous experience in the use and development of R/python packages for biological omics data analysis would be an asset

Good communications skills in an interdisciplinary environment

Offer

Fully-funded position for 2 years in the scenic Mediterranean city of Marseille. The expected starting date is January 2023, or as soon as the position is filled. The salary will be based on experience. Applications can be sent directly to paul.villoutreix@univ-amu.fr. Please make sure that your application includes a motivation letter, a detailed CV and the contact information of 2 references.on goes here

Postdoctoral research positions are immediately available in our research group to work at the intersection of single-cell genomics and machine learning. We are looking for two types of candidates: those interested to develop and apply methods (e.g interpretable deep learning for single-cell multi-omics data integration) and those interested to apply and enhance methods for delineating cell context-specific regulatory programs for precision medicine. Postdocs will be working on clinically important questions in cancer and immunology. Postdocs will engage with the broader systems biology communities by presenting work at top conferences, as well as publishing applications of new methods in high-impact journals.

ENVIRONMENT:

-The Osmanbeyoglu Lab is a multi-disciplinary hybrid wet/dry lab at the University of Pittsburgh. We are affiliated with the Department of Biomedical Informatics, Bioengineering, Biostatistics, the Center for Systems Immunology, and UPMC Hillman Cancer Center

-Our projects are funded by NCI, NIGMS, and The Fund for Innovation in Cancer Informatics

-The University consistently ranks in the top 5 nationally for NIH biomedical research funding and the Cancer Center was recently ranked #7 by US News & World Report

-Candidates may be eligible to apply for the enhanced stipend and career development funding provided as a Hillman Postdoctoral Fellow for Innovative Cancer Research.

QUALIFICATIONS:

Ph.D. in an applied quantitative discipline, such as computational biology, bioinformatics, biostatistics, mathematics, or computer science with a strong interest in translational biomedical research. Ideal candidates would have publications demonstrating experience with code development, applied mathematics, machine learning, deep learning, and/or computational biology. The candidate should 1) be able to work independently and as a member of a team, and 2) be hard-working, motivated, and eager to learn with an outstanding work ethic.

TO APPLY:

If interested, please send an email to osmanbeyogluhu@pitt.edu including your CV (with references) and research interests. Please put the words “POSTDOC-APPLICATION-2022” in the subject line.

Want to devote your expertise in machine learning to accelerate the pace at which new medicines are found?

We are looking for postdoc candidates who want to do research in analyzing massive collections of cell images, towards potentially revolutionizing drug discovery.

Our lab’s mission is to uncover biological knowledge by developing advanced methods to quantify and mine the rich information present in images. We are a friendly and motivated team that is passionate about our research. And we want you to join us!

To find out more about the position, view the detailed description https://broad.io/mlcbpostdoc

The Fudenberg group at the University of Southern California (USC) has long-term funding to support multiple postdoctoral fellows to develop computational approaches to identify and answer fundamental questions in 3D genome biology.

Our long-term goal is to be able to read in DNA sequence and predict how it might organize in any given cellular context, as well as its impact on processes from gene regulation to recombination. For proteins, the path from sequence-to-structure-to-function has been relatively well explored. There is currently an incredible opportunity to do that for 3D genome folding. Potential projects in our group can involve machine learning, biophysical simulations, or both. We are excited to develop new approaches for: sequence-based design of DNA folding, discovery of new 3D genome folding regulators, and probing mechanisms of chromosome folding. Numerous opportunities are available for collaboration with experimental groups.

Our group is part of the Quantitative and Computational Biology Department at USC, which hosts an incredible range of computational biology research all on one floor (https://www.qcb-dornsife.usc.edu/). USC is in the center of Los Angeles (https://dornsifecms.usc.edu/life-in-la/) and is surrounded by opportunities to enjoy art, music, culture, food, and nature.We currently collaborate with researchers with backgrounds ranging from theoretical physics, to computer science, to chromatin biology, and welcome researchers excited by interdisciplinary science. For more information, see https://fudenberg.team/.

Qualifications:

- PhD in Computational Biology, Computer Science, Physics, Applied Math, or demonstration of a similarly strong quantitative and computational skillset

- Previous research experience with genomic data is preferred but not required.

- Commitment to working collaboratively and respectfully with a multidisciplinary team.

Applicants should send via email a 1-2 page cover letter, a CV, and contact information for three references. The cover letter should describe past and current research interests, including how the latter would be enriched by time in our group.

The University of Lincoln is seeking to appoint a Post-Doctoral Research Associate within the School of Computer Science. This position is externally funded by the EPSRC project “Hierarchical Deep Representations of Anatomy (HiDRA)” (https://gow.epsrc.ukri.org/NGBOViewGrant.aspx?GrantRef=EP/W011794/1), led by Dr James Brown (https://staff.lincoln.ac.uk/jamesbrown). The project is an interdisciplinary collaboration with Dr Sara Wells and colleagues at the Mary Lyon Centre at MRC Harwell (https://har.mrc.ac.uk), focused on developing deep learning approaches for musculoskeletal phenotyping.

This project calls for an enthusiastic and self-motivated early career researcher interested in working at the intersection of the computational and biomedical sciences. Candidates should have, or expect to soon obtain, a PhD in a relevant discipline and experience in computer vision/deep learning. They must also have strong mathematical and coding skills, and preferably some experience in open-source software development. Specific experience in biomedical image analysis is preferred but not required. The post will be fixed term for 27 months.

As the successful candidate, you will join a friendly and diverse team of postgraduate students with interests in computer vision, machine learning, and biomedical imaging. Your project will be focused on developing deep learning approaches for the detection of skeletal phenotypes from x-rays of mice. Using a large annotated dataset produced by the International Mouse Phenotyping Consortium (IMPC), you will develop a novel approach to classifying a wide range of skeletal anomalies from multi-view input. As an interdisciplinary project, you will also work closely with colleagues from the mouse genetics community to develop tools for automated annotation in a high-throughput context. You will have the opportunity to disseminate your research via internationally leading journals and conferences from both the computational and biomedical sciences. You will be supported in your continuing professional development and will have access to a suite of training courses offered by the university on topics such as grant writing, project management, supervision, and leadership. You will also be provided with opportunities to teach and supervise students at undergraduate and postgraduate levels.

The University of Lincoln has been recognised as one of the UK's most successful young universities, based in the beautiful and historic city of Lincoln. In the School of Computer Science, over 80% of our research was recognised as internationally excellent or world-leading in the Research Excellence Framework 2021, ranking joint 9th in the UK for research impact.

For informal enquiries about the project, please contact the Principal Investigator, Dr James Brown: jamesbrown@lincoln.ac.uk.

Computational Biology Postdoc, joint between the Dumitrascu Group and Simons Group at Cambridge University, for statistical analysis of multi-omic data with applications in developmental biology.

Complete job description: https://www.jobs.cam.ac.uk/job/36087/

Link to lab

Two postdoctoral fellow positions are available to study transposons and somatic mutations in various human conditions at Boston Children's Hospital (Genetics & Genomics Division) and Harvard Medical School. The projects involve the development of novel computational methods for single-cell and long-read sequencing technologies as well as the integrative analysis of various types of genomic/transcriptomic/epigenetic next generation sequencing (NGS) data.

Transposons have numerous nearly identical copies in the human genome and continuously create novel insertions in human germlines and somatic tissues. Once considered junk DNA, transposons are now recognized as playing an important role in many aspects of human biology and diseases. Somatic mutations present in a small fraction of cells or in single cells have also been implicated in various developmental and degenerative human diseases. Transposons and somatic mutations, however, are two of the most challenging biological entities to detect and validate, but recent advances in single-cell and long-read sequencing will allow us to systematically investigate them.

Alice Lee's laboratory has a track record with both transposons and somatic mutations of developing creative computational methods and performing rigorous analysis for single-cell and other high-throughput NGS data. Postdoctoral fellows will have ample opportunity to work with top experimental and clinical collaborators in the Boston area and beyond to solve real-world biomedical problems and to explore the frontiers of knowledge on transposons and somatic mutations.

Details about the laboratory can be found at http://compgen.hms.harvard.edu

Ideal candidates will have a PhD in computational biology/bioinformatics/computer science or other quantitative field and satisfy at least one of the following criteria:

• Proven ability to develop computational methods for NGS data or to perform integrative bioinformatic analysis with large NGS datasets

• Strong mathematical/statistical background and highly motivated for biomedical research

• Strong programming/cloud computing/IT background with high motivation to perform biomedical research

The Lee lab also has a wet lab to validate computational models/predictions within the lab.

Candidates with excellent wet lab experimental skills who intend to pursue their own experiments along with training in computational research are encouraged to apply.

Interested applicants should send a CV including three references, and a brief statement of research interests along with best papers (up to three) to ealice.lee@childrens.harvard.edu with [Application] in the subject line.

Link to lab

Learning the immune and protein shape space

NIH funded postdoctoral positions available in the group of Prof. Armita Nourmohammad at the University of Washington, Seattle.

Project description:

The adaptive immune system can mount a specific response against a multitude of pathogens, through molecular recognition grounded in complex biophysics of protein-protein interaction. We aim to develop data-driven approaches with machine learning to characterize a representation of protein interactions in general, and of immune receptors, in particular. To learn interpretable and biophysical models for proteins, we will develop equivariant neural networks that take protein structures as input and through transformations that respect the physical symmetries in the data. The learned representation reflects the relevant biophysical properties that determine a protein receptor’s stability, and function, and can be used to predict immune recognition and to design novel immune receptors and antibodies against a desired target.

Environment:

The group is well integrated in the computational biology efforts at the University of Washington and the neighboring Fred Hutch Institute, in beautiful Seattle. This project offers the postdoctoral fellow to lead exciting collaborations with experimental and computational teams in protein science and immunology at both of these institutions.

Skillset:

The projects will involve development of novel AI techniques suitable for large scale analysis of protein 3D structures. Successful applicants will have strong quantitative and computational skillset and ideally familiarity with ML techniques. They will have a PhD in a relevant field (e.g. Theoretical Physics, Applied Math, Computer Science, Computational biology) or will be on track to obtain one before joining the lab. Previous work in biology is not necessary but the applicant should be motivated and committed to work in a multidisciplinary team.

Details about these positions and the application process can be found here:

sites.google.com/uw.edu/statphysevol/join-us

Link to lab

Keiser Lab at the University of California, San Francisco combines machine learning and chemical biology methods to investigate how small molecules perturb protein networks to achieve therapeutic effects. The lab has a few open staff and postdoc positions available. Please take a look at the list of open positions below:

Postdoctoral Scholars

We’re looking for highly motivated postdoctoral candidates with a background in machine learning, pathology, biomedical image analysis, or related fields. To learn more about the open postdoctoral positions with Keiser Lab visit our website at www.keiserlab.org/jobs/.

Research Data Analyst

The Research Data Analyst acquires skills and knowledge of professional concepts in research data analysis, with a focus on machine and deep learning. Candidates will work with biomedical research data such as pathology whole slide images, simulated molecular data, phenotypic drug screening data from model systems, and/or transcriptomic data. Also, opportunities to work on small projects or segments of projects with limited scope and complexity. For more information about the position and to apply visit sjobs.brassring.com/TGnewUI/Search/Home/Home?partnerid=6495&siteid=5861#jobDetails=3138928_5861re

We are seeking an associate computational biologist to join a new team at the Broad Institute to build a Human Gene Regulation Map. This effort will seek to understand the fundamental wiring of the noncoding genome and build a reference map for uncovering biological mechanisms on common genetic diseases. Key investigators involved: Jesse Engreitz, Melina Claussnitzer, Vidya Subramanian, Kasper Lage. We are looking for an individual with experience in high-throughput genomics and data analysis to join this team, which will make fundamental discoveries in mapping gene regulation in various cell types and tissues, understanding cellular programs, and developing new tools to uncover mechanisms of disease.

More information: https://broadinstitute.wd1.myworkdayjobs.com/broad_institute/job/Cambridge-MA/Associate-Computational-Biologist_7322

Noetik is an oncology therapeutics company fusing the cutting edge of machine learning and spatial biology to bring transformative therapeutics to patients. We are building a machine learning focused computational bio team with complementary perspectives and experiences. Seeking candidates with expertise in traditional computational bio pipelines and published research with multiplex imaging and/or spatial omics, as well as experience in or strong enthusiasm for deep learning. We’re laying the groundwork to build an unmatched collection of built-for-machine learning multimodal data, and we’re building data and machine learning infrastructure to max out our team’s leverage over it from day one. We’re also open to passionate candidates with a broad range of expertise who want to have an impact on cancer.

You will join a founding team with a track record of building tech-enabled drug discovery from seed through IPO, and experience moving molecules from discovery to the clinic. Come build the future with us!

To apply, reach out with a brief note of interest to: info@noetik.ai

Contact: rico@retro.bio

Retro develops therapies for diseases driven by the biology of aging.

We work on (1) partial reprogramming, (2) blood factors, and (3) autophagy to rejuvenate and restore function to cells, tissues, and organisms.

We are recruiting a Computational Biologist to join our growing bioinformatics team. You’ll be joining as part of the early team of a rapidly evolving startup that has a long-term vision and extreme financial stability. Candidates can look forward to helping set up and scale a focused research program in collaboration with a world-class team of scientists and engineers with diverse technical backgrounds. You will wear many hats and be challenged with new problems necessitating original thought.

Retro generates copious single-cell -omics data. You will be integral to experimental design and drive computational analysis of molecular experiments in close collaboration with experimental biologists. You will also be responsible for building robust models of aging across cell states and tissues.

Why Retro?

10x faster iteration loops than big pharma & academic labs

Extensive vertical integration: we own the full stack

You will work with everyone across the company

A lot will change during this early stage, providing opportunity for significant impact

It is not for the faint of heart

Your primary responsibilities:

Leading the development and deployment of machine learning-based biomarkers of cellular state, age, and function

Tieing scRNA-seq, scATAC-seq, DNA methylation profiling, imaging, and proteomics assays to cellular function

Analyzing and deriving meaningful insights from unique high-throughput datasets across our different scientific programs

Building the next generation of interpretable mathematical models and software tools for biotechnology

Ideal qualifications:

Demonstrated ability to work independently and think critically

Python programming skills exemplified by tool development

Experience working with scRNA-seq, scATAC-seq, methylation, imaging or proteomics data

Knowledge of and experience with machine learning, deep learning, and Bayesian statistics

Experience working with biological systems in both experimental and computational settings

Extensive development experience with hallmark machine learning and data science frameworks (i.e. Pandas, Scikit-learn, PyTorch, Tensorflow)

You may be a good match for this role if you are:

A hacker: you build quickly, information finds its ways to you

Enthusiastic about rapidly and creatively experimenting, learning, and constantly improving

Excellent at explaining technical concepts clearly with an open communication style

Deeply care about aging and extending healthy human lifespan

Unlearn was founded in 2017 by a team of world-class machine learning scientists to eliminate trial & error in medicine using novel applications of artificial intelligence and statistical modeling.

Our current focus is to drive clinical trial timelines towards zero. Enrollment challenges and timeline delays plague clinical trials. Unlearn has invented a type of randomized controlled trial called a TwinRCT, which generates reliable evidence while enabling the use of smaller control groups than traditional trials. TwinRCTs complete enrollment in less time, are more attractive to potential participants, and provide a regulatory-suitable method for using machine learning-based prognostic models trained on historical trial data to improve future clinical trials.

Unlearn has recently raised a Series B of $65 million in venture capital from top tier investors such as Insight Partners, Radical Ventures, 8VC, DCVC, and DCVC Bio. We have offices in Cambridge, MA and San Francisco, CA. This position can be remote within the US.

ABOUT THE ROLE

Machine Learning Engineers innovate on Unlearn’s approach to build state-of-the-art ML systems for generating Digital Twins – predictions of a patient’s future health outcomes given knowledge of their current and past medical history. ML Engineers at Unlearn come from a wide range of disciplines, and have honed their craft through their work enabling impactful research at top academic and industrial labs, or through their experience delivering robust and reliable ML products and systems. Successful ML Engineers at Unlearn are entrepreneurial in their approach; feeling a strong sense of end-to-end ownership of their mission, they investigate broadly to find the right tools and techniques to help their teams succeed. Successful ML Engineers are also highly collaborative, working as equal partners in interdisciplinary teams to achieve great things together.

RESPONSIBILITIES

- Design, implementation, and maintenance of systems for both training and serving ML models.

- Translate on-paper proposals for ML approaches into reliable and efficient implementations.

- Training, tracking, optimization, and fine-tuning of ML approaches.

- Design, implementation, and maintenance of software libraries for machine learning.

- Measure, analyze, and report on the health of deployed ML systems and products.

- Track state-of-the-art with respect to ML engineering tools and approaches.

- Optimization of techniques and methods to improve training & inference efficiency.

REQUIREMENTS

- B.S. in Mathematics, Computer Science, Engineering, or Physics.

- Demonstrable expertise in software engineering and processes for collaborative software development.

- Solid fundamentals in mathematics (stats, linear algebra, etc.) and computer science (algorithms, data structures, architecture).

- Significant experience with machine learning frameworks such as Pytorch & TensorflowFluency with Python and its software ecosystem.

- Familiarity with high-performance and distributed computing.

- Track record of delivering successful industrial or academic ML projects.

PREFERRED REQUIREMENTS

- An M.S. or Ph.D. focusing on high-performance computing or machine learning.

- A record of publication contributions which used systems you developed to deliver impactful research results.

- Contributions to well-known open-source ML tools or frameworks.

- Post-graduate industry experience or previous internships.

- Previous experience with unsupervised ML, EBM, NLP, LLM, or reinforcement learning.

- Experience using AWS cloud computing services.

- Full-ML-stack experience: delivering ML services from conception to production system to maintenance and iterative improvement.

TO APPLY VISIT OUR WEBSITE: https://jobs.lever.co/UnlearnAI

Amgen has new openings for computational protein designers (wetlab and drylab) and software engineers (ML and non-ML)! These are flexible in both background (so apply if you're at all interested) and many are flexible in location (as much remote or on-site as you'd like). We would be very excited to have people start right away, but if you're a bit out from your next step, we can be flexible there as well. Background in any combination of the following would be great: machine learning, deep learning, reinforcement learning, NLP, vision, PyTorch/TensorFlow/JAX/etc, cloud compute, protein biochemistry, structural biology, and Rosetta.

Recursion is a clinical-stage biotechnology company integrating technological innovations across biology, chemistry, automation, data science and engineering to industrialize drug discovery and radically improve the lives of patients.

Our primary data type is an imaging assay of human cellular disease models and compound treatments run at a massive scale (> 1.8M images per week, > 9PB of data to date). We integrate that data with transcriptomic and proteomic read-outs to understand disease etiology and discover therapies and validate those findings with secondary assays, animal studies and patient trials. Our data science team is stacked with domain expertise in computer vision, machine learning, computational biology, digital chemistry and applied statistics and they work side-by-side with cancer biologists, neuroscientists, immunologists and chemists to develop tools and methods to turn our experimental data into treatments across a broad range of disease areas.

If you’re interested in applying your expertise in machine learning, computer vision, data science or ML engineering to solving some of the hardest, most meaningful problems facing human health today, come join us and do the most impactful work of your life.

Learn more about opportunities here: https://www.recursion.com/careers

The critical bottleneck in drug discovery remains poor understanding of the biological mechanisms underlying disease. As a result, often we don’t know why patients become sick; and many drug candidates fail in trials while numerous patients with devastating diseases remain untreated. Relation is pioneering a “Lab-in-the-Loop” that can chart and navigate biology at every step of drug discovery, from predicting cell states to the validation of new targets. Working from real cells provided by proprietary biobanks, Relation’s technology generates omic data that provide direct insights into critical biological relationships that are fed directly into its platform.

Relation Therapeutics is looking for a Director/Senior Director of Machine Learning, reporting to the Head of Machine Learning (currently the CTO). The successful candidate will lead an interdisciplinary team (including Data Scientists, Data Engineers and experimental scientists) to deliver our strategic priorities in machine learning and to help build our proprietary technologies. This includes contributing to the design and delivery of machine learning projects using the latest methods and engineering best practices. You will have a deep understanding of contemporary ML techniques, experience of leading high-performing ML teams and a track record of delivery. You will also lead basic ML research (in partnership with other senior group members) and continue to engage with the external community, through papers at the major ML conferences and broader engagement activities including technical blogs etc.

By joining Relation, you will be part of an exceptionally talented team, learn a broad range of skills within and outside your area of expertise, help us shape our culture and strategic direction and ultimately, make a positive impact in patients’ lives.

Prescient Design seeks exceptional researchers and engineers who have a demonstrated research background in machine learning and structural and computational biology. The group provides a dynamic and challenging environment for cutting-edge, multidisciplinary research including access to heterogeneous data sources, close links to top academic institutions around the world, as well as internal Genentech Research and Early Development (gRED) partners and research units. The team's mission is to develop and apply methods for molecular design, both for small and large molecules. Researchers will primarily focus on the deep learning subfield of machine learning but should be broadly interested in methods capable of effective representation learning that can help drive and sharpen the research questions we study. We have a number of full-time and postdoctoral roles including across Engineering, Structural & Computational Biology, and Machine Learning teams.

Full-time Roles:

• Machine Learning Engineer

• Data/Infrastructure Engineer

• Machine Learning Scientist

• Structural & Computational Biologist

Postdoctoral Fellowships:

• Machine Learning

• Structural & Computational Biology

More details about opportunities at Prescient and Genentech can be found at: https://careers.gene.com/us/en/c/data-science-ai-ml-jobs.

Absci is the drug and target discovery company harnessing deep learning and synthetic biology to expand the therapeutic potential of proteins. We built our Integrated Drug Creation™ Platform to identify novel drug targets, discover optimal biotherapeutic candidates, and generate the cell lines to manufacture them in a single efficient process. Our goal is to enable the development of better medicines. We Translate Ideas into Drugs™. Based in Vancouver, Washington, ten minutes from Portland, Oregon, we’re located within an hour of world class alpine terrain and rugged Pacific coastlines. Check out this short video to learn more and see how our #Unlimiters are changing the world one protein at a time: absci.com/joinus

We are seeking Research Scientists to join our world-class Artificial Intelligence (AI) team and advance generative models for protein drug design. As a Research Scientist, you will develop advanced machine learning techniques that will be deployed for the creation of lifesaving drugs. We are looking for people who can draw on significant expertise in deep learning or related disciplines such as natural language processing, protein design, and computer vision, to develop innovative models that can learn from and generate new proteins. This position can be Remote, Hybrid or Onsite in Vancouver, WA or New York, New York.

Example responsibilities

Design, implement and evaluate cutting-edge generative models for protein design

Effectively report and communicate research findings to AI and wet-lab teams across the company

Develop sampling techniques for designing diverse proteins

Collaborate with data scientists and wet-lab biologists on the design and integration of wet-lab experiments

Deploy large-scale distributed training systems on our in-house A100-based supercomputer

Qualifications

PhD in Machine Learning or equivalent practical experience

Publications at major machine learning conferences & scientific journals, or extensive experience creating deep learning models in industry

Strong Python programming skills, including with Numpy, Scipy, and Pandas, with emphasis on data science and machine learning applications.

Experience designing and training complex deep learning models in PyTorch or related platforms

Demonstrated ability to work collaboratively on projects with multiple contributor.

Preferred (but not required):

Industry experience developing and training deep learning models, preferably in the life-sciences domain

Background in structural biology

Experience with antibody / biologics engineering

NGS analysis experience

Experience with large-scale multi-node training on an HPC GPU cluster

Hands-on experience developing deep generative models for language modeling or geometric applications

We seek candidates who will dive into our creative company culture that’s collaborative, multidisciplinary, and committed to a big vision for positive impact. We are defying conventions and innovating without boundaries. We are disrupting an industry with bold ideas and passionate pursuit of new possibilities. We are looking for original thinkers, creative scientists, and data-devoted gurus. Successful candidates will be excited to work in a dynamic environment and contribute as a key member of a project team. If this sounds good to you, we invite you to join us in our quest to redefine possible.

Absci offers highly competitive salaries and benefits, including medical and dental insurance, paid time off, breakfast and lunch, and 401(k) with a generous company match. Legal authorization to work in the U.S. is required. Absci is committed to equal employment opportunity and non-discrimination for all employees and qualified applicants without regard to a person's race, color, gender, age, religion, national origin, ancestry, disability, veteran status, genetic information, sexual orientation or any characteristic protected under applicable law. Absci will make reasonable accommodations for qualified individuals with known disabilities, in accordance with applicable law. Absci offers a dog-friendly work environment - bring your pup along for the ride.

Apply at: https://www.absci.com/careers/roles/?gh_jid=5034980003

BAYESIAN STATISTICAL METHODS FOR HIGH-DIMENSIONAL MULTI-OMICS

EUNICE KENNEDY SHRIVER NATIONAL INSTITUTE OF CHILD HEALTH AND HUMAN DEVELOPMENT, BETHESDA, MD AND SURROUNDING AREA

Position Description:

The Biostatistics and Bioinformatics Branch (BBB) within the Division of Intramural Population Health Research (DIPHR) at the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD), National Institutes of Health is soliciting applications from post-doctoral level scientists interested in the development and application of Bayesian statistical methods focusing on high-dimensional multi-omics measurements, including microbial metagenomics, metabolomics, human RNAseq and diet to further our understanding of host-microbe interactions and microbe-metabolite interactions. The successful candidate will have the opportunity to develop and train interpretable Bayesian machine learning algorithms on large publicly available repositories such as the Sequence Read Archive, with the goal of designing new clinical studies and enabling causal insights on clinical interventions.

Branch members conduct independent methodological research relevant to the design and analysis of epidemiological, behavioral and intervention studies. Much of the statistical research is motivated by collaborative research focusing on human reproduction and development, pregnancy, and child and adolescent health with DIPHR investigators. Postdoctoral fellows will have access to supercomputing resources and have the opportunity to collaborate with statistical, bioinformatic and clinical investigators within and outside of DIPHR on important studies. Candidates eligible to work in the USA, with an earned doctoral degree in bioinformatics, biostatistics, computer science, engineering or a related discipline within the past five years are invited to apply. We will give preference to candidates with methodological and computational interest and experience in Bayesian inference and/or machine learning and a background in Pytorch and/or Stan. Excellent communication skills with keen interest in applied biomedical research are required. Stipend is competitive and commensurate with research experience and accomplishments.

To Apply:

Interested candidates should email a complete application package consisting of: 1) a curriculum vitae (CV); 2) official transcripts for undergraduate and graduate degrees; 3) a statement of research interests to be pursued during training; and 4) three letters of reference to Dr. Neil Perkins at perkinsn@mail.nih.gov.

Further information about the Biostatistics and Bioinformatics Branch and Division may be found at: https://www.nichd.nih.gov/about/org/dir/dph/officebranch/bbb. These positions will remain open until qualified applicants are recruited. All inquiries about the position should be directed to Dr. Shyamal Peddada at shyamal.peddada@nih.gov.

Link to lab

We’re excited about a new initiative applying recommender systems to genomics, and are looking to hire for multiple positions. Due to the pandemic, we are currently working mostly remote, and have flexibility to consider applicants from across the USA and beyond. Positions available immediately, until filled.

Background and directions:

The traditional way of analyzing genomics data is severely limited due to a chronic lack of broader context: most experiments and analyses are performed in isolation, and high specialization levels of individual scientists preclude a birds-eye view across datasets. At the same time, consumer-facing web businesses have long understood the value of learning from patterns collected across large corpora of data, to better serve customers, maximize investment returns and prioritize future directions. This gap between current practice in genomics and ultimate potential forms the overarching motivation for our work: we aim to enable the full potential of large-scale genomic datasets through the use of machine-assisted approaches. These ideas represent an essential and inevitable transition towards “augmented genomics”, a new field in which the work of genome scientists is supplemented by data-driven machine intelligence.

Available Positions:

We’re currently hiring computational postdoctoral researchers as well as otherwise experienced computational scientists.

Domain expertise in computational biology (in particular chromatin genomics) and recommender systems is preferred but not strictly required. What is important, is your enthusiasm for the subject matter, and an aptitude for large scale data exploration and analysis.

An ideal candidate should possess at least several of the following:

- PhD in (computational) genomics or a related field (for the postdoc position)

- Publications in peer-reviewed journals and conferences (for the postdoc position)

- Experience managing projects and mentoring people

- Fluency in Python and/or R

- Good at (graphically) summarizing large amounts of data

- Demonstrated experience with applying machine learning models to genomics data

- Working knowledge of information retrieval processes or recommender systems

- Academic background and expertise in (a field related to) chromatin genomics

- A curious mind, with great attention to detail

- Good communication skills, both spoken and written

If you are unsure about how you could contribute or fit in, please do not self-select yourself out, but let’s talk. People from traditionally underrepresented groups are particularly encouraged to apply: we want to hear from you. If you have relevant experience and want to apply this to genomics, this is a great opportunity to make a big impact!

Research environment:

Dr. Meuleman’s research interests span genome organization, regulatory genomics, computational epigenomics and large-scale data integration & visualization. We operate as a small group of 5-6 people, and aim for a research environment driven by curiosity, collaboration, veracity, and inclusion, so that we can do our best work together. This environment includes a strong commitment to training and teaching of skills required, and an expectation of working with enthusiastic self-motivating people.

Working at the Altius Institute:

The Altius Institute for Biomedical Sciences is a non-profit research institute with ~80 people, located on Seattle’s waterfront right next to Pike Place Market. Beyond great food, coffee & culture, Seattle offers plenty of skiing, hiking & camping opportunities less than an hour away. Altius offers amazing employment benefits, including matched retirement fund contributions, generous time off (incl. paid holidays and parental leave), great medical/dental/vision plans, commuter benefits & much more.

Other available positions:

In addition to the positions listed above, we further have openings in the areas of:

- regulatory genome organization and annotation,

- large-scale genomic data visualization and

- synthetic sequence generation using machine learning models.

How to apply:

To apply, please submit the following material to hiring@meuleman.org

- curriculum vitae

- a cover letter outlining previous experience, current interests and career goals

- contact information for three references

Inquiries about these and other positions are welcome and encouraged. Please contact Dr. Wouter Meuleman by email (wouter@meuleman.org) or via Twitter DM (@nameluem).

Link to lab

We are looking to hire several postdoctoral fellows to work on mathematical foundations of single cell analysis. This exciting field lies at the intersection of probability, statistics, optimization, and developmental biology. New measurement technologies like single-cell RNA sequencing are bringing 'big data' to biology.

Our group develops mathematical tools for analyzing time-courses of high-dimensional gene expression data, leveraging tools from probability and optimal transport. We aim to develop a mathematical theory to answer questions like How does a stem cell transform into a muscle cell, a skin cell, or a neuron? How can we reprogram a skin cell into a neuron? We model a developing population of cells with a curve in the space of probability distributions on a high-dimensional gene expression space. We design algorithms to recover these curves from samples at various time-points and we collaborate closely with experimentalists to test these ideas on real data. Motivated by this theory, we have recently designed an experimental protocol to collect thousands of time-points over the course of C. elegans development (with collaborators Nozomu Yachie and Kenji Sugioka). This is a 100-fold increase in temporal resolution over state of the art. There are also opportunities in spatial transcriptomics.

For samples of recent work see:

Optimal-Transport Analysis of Single-Cell Gene Expression Identifies Developmental Trajectories in Reprogramming

A Unified Framework for Lineage Tracing and Trajectory Inference

Towards a mathematical theory of trajectory inference

Funding is available for 2 years, renewable up to 4 years contingent on successful performance.

Working Environment

The successful candidates will be based in Geoffrey Schiebinger’s group in the Department of Mathematics at the University of British Columbia in Vancouver, Canada. They will have opportunities to collaborate with both experimental and theoretical collaborators. On the experimental side, we have active collaborations with Peter Zandstra, Nozomu Yachie, Greg Wray, Philip Benfey, Ken Harder, Kenji Sugioka. On the mathematical side, we have active collaborations with Omer Angel, Yaniv Plan, and Young-Heon Kim. Contact To apply, please send a CV and cover letter describing interest and previous experience to Geoffrey Schiebinger (geoff@math.ubc.edu). We are committed to diversity and especially encourage members of underrepresented communities to apply.

Link to lab

Advancing ML for immunology

Unique opportunity for talented computational post-doc to bridge computational/translational discovery in top ML/bio lab together with a new Boston-based startup. You will advance fundamental methods for autoimmune disease immunogenomics under the mentorship of Prof. Debora Marks @ Harvard Medical School and the founding team @ JURA Bio.

Ideally you will have a track record of developing ML methods. You will have the opportunity to exert direct influence over translational efforts for cutting-edge cell-based therapeutics.

Required:

- Ph.D. in computer science, statistics, biophysics, or equivalent

- Expertise in one or more general-purpose programming languages (such as Python or C/C++) and preferably one probabilistic programming language (STAN, Edward, Pyro)

- Experience with at least one machine learning library (such as Tensorflow or pyTorch)

Preferred:

- Knowledge of immunology, especially autoimmune diseases

- Familiarity with handling large biological datasets, especially sequence data and single-cell sequencing data/genomics

Responsibilities:

You will help manage a multi-site study and will oversee the data analysis and data sharing teams. Your responsibilities span biological data analysis, machine learning model building, computational optimization, and experimental design of high-throughput lymphocyte libraries. There will be opportunities to develop probabilistic generative models and apply rigorous theoretical approaches from Bayesian optimization.

Apply at: tiny.url/immML

Link to lab

PhD Project in Computational modelling to understand and predict protein variant effects at the Department of Biology, Faculty of SCIENCE, University of Copenhagen

One or more PhD scholarships are available from Feb 1st, 2022, or as soon as possible thereafter, in the PRISM centre, Department of Biology, Faculty of Science, University of Copenhagen, Denmark. The research within PRISM bridges protein biophysics and genomics using computational and experimental methods.

The PhD projects in this call are focused on computational modelling within structural bioinformatics of protein structure and sequence.

The project

The PhD students will work on one or more of the subprojects within PRISM. Long-term goals include developing predictive and mechanistic models for how genomic variation in protein-coding regions (protein variants) affect the stability, interactions and function of proteins. We are in particular interested in developing predictive models that can be interpreted in terms of specific biological mechanisms. For an introduction to the computational aspects of the research see e.g. our recent review (Stein et al, TiBS, 2019) and recent research papers (e.g. Cagiada et al, Johansson et al, Høie et al).

Research topics for the PhD projects include:

Predicting effects of variation on protein stability and protein function across entire proteomes

Development and application of prediction methods to interpret genomic variation

Using methods from structural bioinformatics and protein sequence analysis to perform large scale analysis of human genetic variation

Combining data from multiplexed assays and computational methods to understand protein stability and degradation in a cellular context

Developing methods to analyse multiplexed assays of protein variant effects

Who are we looking for?

We are seeking motivated applicants with an MSc degree in bioinformatics, biophysics, physics, chemistry or biochemistry or similar fields, ideally with some prior research experience (e.g. through MSc projects) within one or more of these areas:

Structural bioinformatics

Computational analyses of the effects of protein sequence variation on protein function and stability

Large scale analysis of sequencing data focusing on proteins

The ideal candidate has a quantitative mindset and some programming experience, but also a keen interest in and understanding of protein chemistry and biophysics.

More information at link.

Link to post

Reach out to Jes Frellsen if you have “if you have a strong background in ML/DL/CS/Stats, are interested in deep generative models and want to work with [him].”

At DTU Compute you will be part of an internationally renowned research environment counting top class scientists, supervisors and numerous PhD students like yourself. In a combined role (full time with full time salary) you will be both a student and a co-working scientist. When finished, you have build valuable network, friendships as well as achieved research results to be proud of – and by that you have created the best possible foundation for your future career in academia or industry.

Turn your ideas and scientific curiosity into valuable knowledge that makes a difference.

Now you have finished or are close to finishing your Master’s degree in the fields of mathematics, statistics or computer science. And then what? We have the answer. At least if you dream of turning your ideas into technology for the benefit of people by pushing the boundaries of current knowledge in science and engineering.