Research Scientist, Life Sciences

Key Responsibilities

• Build, run, and maintain analysis pipelines for experimental programs including sequence analysis at petabyte scale, structural bioinformatics, phylogenetic and comparative genomics, design and analysis of high-throughput functional screens, and biological sequence modeling.
• Partner directly with experimental biologists to design experiments that produce high-quality data and rapidly turn results around to inform the next experiment.
• Draw on scientific literature, curated biological knowledge bases, and primary data to generate and prioritize hypotheses for experimental follow-up.
• Stand up and maintain the team's computational infrastructure including data ingestion, workflow orchestration, internal databases, and interfaces accessible to researchers and AI agents.
• Use Claude and internal agent frameworks heavily in daily work, feeding learnings back to model-improvement and product teams as evaluations, datasets, and failure cases.
• Flexibly pick up analyses across projects as priorities shift, emphasizing breadth over a single deep specialty.

Minimum Qualifications

• PhD in computational biology, bioinformatics, genomics, biophysics, machine learning, computer science, or a related quantitative or biological field (or equivalent industry research experience).
• Track record of leading end-to-end computational biology research from question to result, with evidence of impact (e.g., publications, preprints, released datasets/tools, or research that changed a program's direction).
• Demonstrated breadth across multiple areas of computational biology.
• Proficient in one or more scientific computing programming languages; comfortable working on large datasets in Linux and cloud environments.
• Ability to take an ambiguous biological question, scope the analysis, and produce actionable results for experimentalists.
• Strong communication skills for conveying computational results to both biologists and ML researchers.

Preferred Qualifications

• Comfort navigating ambiguity and developing solutions in rapidly evolving research environments.
• Results-oriented with a bias towards flexibility and impact.
• Hands-on experience in experimental biology or track record of designing experiments alongside experimentalists.
• Experience building tools, pipelines, or agentic systems on top of LLMs, or training models on biological sequence data.
• Deep expertise in one or two areas of computational biology (e.g., structural biology, metagenomics, single-cell genomics, or protein design) on top of required breadth.