About the RoleBring deep biological expertise to the data, tasks, and analyses behind our models. You will turn questions in genomics, gene regulation, protein biology, or systems biology into well-defined computational work and use sound judgment to interpret the results.
The role can be shaped around a strong specialty, including data curation, bioinformatics pipelines, or model evaluation. You will partner with model researchers and experimental collaborators to build datasets and analyses that support useful scientific work.
What You Will Do- Curate and integrate large biological datasets, with clear provenance, quality control, and documented assumptions.
- Build reproducible bioinformatics and analysis pipelines across sequencing data, functional genomics data, single-cell data, perturbational screening data, protein data, or other data relevant to your specialty.
- Help design data mixtures and sampling strategies for model training. Investigate how dataset composition, assay effects, duplication, and biological coverage affect downstream results.
- Define biologically meaningful tasks, endpoints, and baselines with modeling and evaluation teams. Investigate model predictions and failure modes in the context of available biological evidence.
- Work with collaborators in the wet lab to formulate testable hypotheses, prioritize validation experiments, and generate new training data sets.
What We Are Looking For- An exceptional research record in computational biology, bioinformatics, genomics, or another relevant area of biology, demonstrated through a PhD or equivalent research or industry experience.
- Deep expertise in at least one biological domain, with strong scientific judgment and careful attention to data quality and experimental details.
- Strong Python or R programming skills and experience building reliable, reproducible scientific analyses or software.
- Ability to work between biology, machine learning, and engineering and communicate assumptions, results, and limitations clearly.
- Experience working with agentic coding tools.
Nice to Have- Experience with large-scale biological data curation, data mixing, or bioinformatics infrastructure.
- Experience with biological foundation models or research contributions, datasets, methods, or software used by other scientists.
