Principal Scientist, Translational AI Foundations

Bristol Myers Squibb•Needham, MA
•$166,770 - $202,086

About The Position

Bristol Myers Squibb’s Informatics and Predictive Sciences organization is forming Translational AI Foundations (TAIF), a small team of computational biologists and AI engineers that partners with translational research groups. TAIF converts biomarker analyses currently performed manually into validated, reusable AI agents and workflows, then transfers them to the research groups that will use and maintain them. The role builds shared tools rather than delivering one-off analyses for a single drug program. The Principal Scientist designs, builds, and validates assay-level AI agents and the analysis logic behind them, with the goal of reducing biomarker analyses that currently take weeks to work through to a recommendation to days. The initial focus is spatial transcriptomics and H&E, followed by other biomarker data types, including ctDNA, IHC, cytokine panels, RNA-seq, PK/PD, and clinical data. The role uses real program data, works directly with program scientists and translational research groups, and establishes scientific standards for a shared engineering platform. The position is primarily focused on building agents, writing expert-approved specifications, and setting test cases and release criteria. It also leads initial spatial pilots, works with research groups to co-develop and validate tools, and maintains validation tests after handoff. Outputs are designed to support program decisions and include interpretations, limitations, recommendations, traceable sources for results, and human review.

Requirements

  • Ph.D. in computational biology, bioinformatics, biostatistics, computer science, a related quantitative field, or a life-science field with substantial computational training, plus 4 or more years of relevant academic and/or industry experience; or a Master's degree with 6 or more years; or a Bachelor's degree with 8 or more years.
  • Hands-on experience analyzing and interpreting high-dimensional molecular data from human tissue, including spatial transcriptomics and single-cell or bulk RNA-seq, through to publication-ready or decision-ready results.
  • Hands-on experience building LLM-based or agentic analysis workflows and evaluating outputs against expert review, reference results, or benchmarks.
  • Strong Python and/or R skills and reproducible analysis practices, with experience turning recurring analyses into reusable tools adopted by other scientists.
  • Clear scientific communication skills and experience working directly with wet-lab, translational, or clinical colleagues who are not engineers.
  • Experience analyzing patient-derived translational data in at least three of the following: IHC, cytokine panels, bulk or single-cell RNA-seq, ctDNA, PK/PD, spatial transcriptomics, and H&E pathology.
  • Working understanding of pharmacodynamic, mechanism-of-action, and mechanism-of-resistance questions in early clinical development.

Nice To Haves

  • Spatial analysis expertise in deep-learning cell segmentation, atlas-based automated cell-type annotation, spatial differential expression, neighborhood analysis, and ligand-receptor analysis.
  • Familiarity with spatial analysis tools and frameworks such as Squidpy, SpatialData, and scverse, and digital pathology tools such as HALO and QuPath.
  • Experience designing AI-output evaluations using benchmark sets, gold-standard cases, reference results, model-consistency checks, checks for unsupported claims, and expert-approved specifications.
  • Reproducible engineering experience with version control, tests, workflow managers such as Nextflow or Snakemake, cloud or HPC compute such as AWS, CI/CD, and packaging analyses as tools or services adopted by others.
  • Experience training and enabling non-engineer scientists through workshops, courses, documentation, co-design, or methods that others subsequently used independently.
  • Prior experience in biopharmaceutical translational research or early clinical development, including biomarker strategy or clinical translational data interpretation.
  • Familiarity with governed data platforms such as Databricks and controlled terminologies or ontologies for biomarker data.
  • Peer-reviewed publications, released software, or deployed analysis portals in spatial or single-cell biology.
  • Depth in several preferred areas, together with sound judgment about whether an output is supported by the data.

Responsibilities

  • Build and maintain AI agents for biomarker data types, beginning with spatial transcriptomics and H&E and expanding to ctDNA, IHC, cytokine panels, RNA-seq, PK/PD, and clinical data.
  • Define agent inputs and outputs, ensure every reported number has a traceable source, and include a human-review step.
  • Develop agent specifications with subject-matter experts, covering biology, data and quality control, approved analysis flows, acceptable and unacceptable interpretations, failure modes, gold-standard cases, and expert reviewers.
  • Define test cases and pass criteria for agent release and conduct periodic peer review of agent outputs.
  • Define and validate biomarker definitions, cutoffs, and derivations, ensuring their scientific correctness as they are encoded in the shared ontology.
  • Own decision-grade output templates that present interpretations, limitations, and recommendations in a form suitable for program decisions.
  • Lead initial spatial transcriptomics and H&E pilots, measure time saved against current practice, and expand to further data types and research groups with validation cases for each pilot.
  • Partner with AI contacts in translational research groups to co-develop tools, review their scientific correctness, and teach methods that enable teams to use tools independently.
  • Maintain each agent's validation tests after handoff to the owning research group and confirm that it continues to pass.
  • Document methods and specifications, mentor junior team members and research-group AI contacts, and help advance computational and AI capabilities across the translational organization.

Benefits

  • Comprehensive benefit plans, including wellbeing support, retirement and financial protection benefits, and medical, dental, vision, life, and disability insurance offerings, subject to plan terms and eligibility.
  • For eligible U.S.-based exempt employees, Flexible Time Off with no set accrual limit, subject to manager approval, and 11 paid company holidays annually.
  • For non-exempt employees, RayzeBio employees, and employees located in Puerto Rico: 160 hours of paid vacation annually for new hires, subject to manager approval, 11 paid company holidays, and 3 optional holidays.
  • Depending on eligibility, additional time-off benefits may include paid sick leave, up to two paid volunteer days per year, summer hours flexibility, and leaves for medical, personal, parental, caregiver, bereavement, or military needs.
  • Eligible employees receive an annual Global Shutdown between Christmas Day and New Year's Day.
  • Potential eligibility for discretionary incentive cash and stock opportunities.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service