About the job
In this role, you will lead and grow a team of exceptional machine learning researchers responsible for co-developing methods for extracting information from in-vitro biology using computer vision and machine learning. You will lead an established team of 5 machine learning scientists, several at the Staff level, and be expected to grow it over time. Your team will partner closely with laboratory scientists to develop biological assays in a tight loop, iterating sample preparation protocols and feature extraction methods in tandem. As the manager of this team, you will be responsible for structuring these collaborations in ways that ensure the success of all teams, and your individual team members, as measured by our ability to drive insitro's therapeutic programs forward through understanding of causal human biology.
Responsibilities
- Lead, mentor, and grow a team of outstanding machine learning scientists to co-develop methods of extracting insights from in-vitro microscopy datasets
- Work closely with laboratory leadership to structure assay development efforts, and empower members of your team to co-develop in-vitro microscopy assays suitable for genetic perturbation screening, often at whole-genome scale
- Ensure the successful translation of assays you develop to insitro’s computational biology
Qualifications
Minimum
- Strong grounding in computer vision and machine learning fundamentals, with practical judgment about where these methods work and where they fail
- Demonstrated experience applying CV/ML to pixel data to extract quantitative features and downstream biological insight
- Working understanding of imaging principles — image formation, microscopy fundamentals, and the artifacts that arise from instruments and sample preparation
- Hands-on experience with cellular imaging datasets (e.g. fluorescence/confocal or label-free microscopy)
- 3+ years of people management, including solid-line management of multiple ICs and at least one senior (Staff-level) scientist or engineer
- Track record of mentoring and growing technical talent day-to-day
- Technical leadership as a decision-maker on projects, platforms, or teams
- Strong communication and the ability to collaborate across functions, including with experimental and clinical life scientists
Preferred
- Experience across additional high-content modalities: temporal phenotyping, spatial proteomics, single-cell or bulk omics, or pooled optical (in-situ) screening
- Familiarity with genetic perturbation screening, ideally at genome scale
- Experience with data-quality methods for imaging — agentic frameworks, VLMs, or self-supervised approaches for QC and classification
- Conversational understanding of a relevant disease area (neuroscience, metabolic disease, or cancer biology)
- Experience contributing to or shaping an imaging/CV software platform