Computational Biologist

Onyx Bio•Berkeley, CA

1d•Onsite

About The Position

Onyx is a research collective building a virtual immune system—a model of how real people respond to infection, inflammation, and treatment. Every person who joins adds to it, helping researchers understand immune disease more deeply and build the next generation of precision medicines faster and more safely. We’re looking for someone who can build and productize our virtual immune system. We work directly with members to collect fully paired data spanning clinical records/real-world data along with multiomic data—including assays from WGS, scRNA (5’/TCR/BCR, 3’/ATAC), proteomics, metabolomics, reactomics, and beyond—all over time as members’ health changes. You’ll be focused on leading efforts to handle all the multiomic data we have, and then utilizing it to power AI scientists, AI models, and other analyses that we will run internally and in partnership with other researchers. You should naturally handle highly ambiguous situations with tenacity, discovering paths forward using both internal and external feedback. The work spans several domains: biology, AI, infrastructure, and product development. You should have demonstrated a high capacity to learn quickly, be meticulous about data quality and rigor, and have a track record of great judgement. At present, the role emphasizes individual contribution, though over time, as the team grows, the candidate will have the opportunity to lead and mentor.

Requirements

PhD or equivalent experience in Computational Biology, Bioinformatics, Systems Biology, Computer Science, or a related quantitative field.
5+ years of industry experience in computational biology, preferably on a small team.
Deep expertise in analyzing multiomic datasets, including single-cell genomics (scRNA, ATAC, TCR/BCR), bulk sequencing, or proteomics/metabolomics.
Demonstrated track record of developing machine learning or deep learning models for complex biological data and biological target/feature discovery.
Strong software engineering and data infrastructure capabilities for productizing models and pipeline architectures.

Nice To Haves

Domain expertise in human immunology, autoimmune diseases, or systemic inflammatory response modeling.
Experience working with electronic health records (EHR), longitudinal clinical datasets, and real-world data integration.
Experience building foundation models or generative AI architectures tailored for biological multiomics.
Proven ability to lead technical teams or cross-functional research initiatives in high-growth startup environments.

Responsibilities

Lead the strategy and execution for processing, analyzing, and integrating multiomic data types (WGS, scRNA-seq, TCR/BCR, proteomics, metabolomics, reactomics) paired with longitudinal real-world data.
Build and deploy AI models, foundation models, and computational infrastructure to model immune system dynamics and extract biological insights.
Drive cross-functional technical initiatives spanning computational biology, AI research, data infrastructure, and product development.
Collaborate with external academic and industry research partners to deliver collaborative translational insights and data productizations.