The Oncology Translational IPS team is seeking a Principal Scientist, Translational Computational Biology, to serve as the computational partner to our oncology drug development programs across discovery, translational research, and early clinical development. You will translate patient-derived molecular, spatial, and clinical data into biomarker hypotheses, patient stratification strategies, indication prioritization, pharmacodynamic readouts, and decision-grade recommendations.
The majority of the role is embedded with oncology drug development programs and clinical development teams. The remainder builds computational capability for the broader portfolio: spatial biology, AI-enabled translational science, and reusable analytical methods. The exact emphasis of that capability work will evolve with portfolio priorities and emerging technologies.
This role is for someone who understands drug development, not only data analysis. We are looking for a scientist with a working understanding of the path from target validation and candidate selection through IND-enabling work and early clinical studies (including dose escalation and expansion), and of the strategic role biomarkers play at each stage, who can carry an interpretation into the forum where the decision is actually made.
What you will have to work withSpatial transcriptomics and spatial proteomics / multiplex immunofluorescence. Dedicated analytical ownership across multiple concurrent oncology programs, on the platforms the team runs today: Xenium, Visium, and Visium HD for spatial transcriptomics, and platforms such as COMET or PhenoCycler for spatial proteomics / multiplex immunofluorescence. Backed by a pan-cancer spatial atlas license, an H&E-to-mIF platform partnership, and cloud compute alongside a translational informatics team that builds its own methods. These platforms are already funded and running; this role exists to realize their scientific value.
Clinical and multi-modal patient-derived datasets from BMS's industry-leading early-stage clinical studies in oncology: the molecular and clinical biomarker data generated by our own early-phase trials, spanning RNA-seq, ctDNA, WES, TCR-seq, and CTC, together with flow cytometry, cytokine profiling, IHC, and proteomics.
Your contributions will influence development strategies and play a vital role in propelling the BMS early-stage oncology pipeline forward, directly impacting the treatment of cancer patients.
You will apply these data across two areas:
- Oncology drug development program, translational, and early clinical development support. The majority of the role. Biomarker strategy; patient selection and stratification; indication prioritization; target validation; IND-enabling and early clinical trial interpretation; data-driven recommendations for program decisions.
- Computational innovation and portfolio capability. The remainder. Spatial biology; AI-enabled translational science; multimodal integration; reusable workflows, automation, and scalable analytical methods that serve the portfolio rather than a single program.
Key ResponsibilitiesOncology drug development program, translational, and early clinical development support- Oncology program partnership. Serve as the translational computational scientist for assigned oncology drug development programs across the discovery-to-early-clinical continuum, from target validation through early clinical studies.
- Biomarker and patient strategy. Shape biomarker strategy, patient selection and stratification hypotheses, pharmacodynamic marker plans, indication prioritization, and enrichment approaches.
- Patient-derived data analysis. Analyze and integrate multimodal molecular, clinical, and translational datasets from oncology studies, including bulk and single-cell RNA-seq, ctDNA, WES, and liquid biopsy, TCR-seq, flow cytometry, cytokine profiling, IHC, proteomics, and spatial readouts.
- Discovery-to-translational support. Use patient molecular data, causal and driver inference, regulatory network analysis, perturbation readouts, and orthogonal evidence to support target nomination, validation, candidate selection, and IND-enabling decisions.
- Decision-grade communication. Translate complex multimodal analyses into clear, decision-grade biological narratives. Every result ships with an interpretation, its limitations, and a recommendation, and you carry that recommendation to the program team, translational review, or governance forum where the decision is made.
Computational innovation and portfolio capability- Spatial biology. Take dedicated analytical ownership of spatial data across the portfolio: spatial transcriptomics (Xenium, Visium, Visium HD) and spatial proteomics / multiplex immunofluorescence (e.g., COMET, PhenoCycler), realizing the scientific value of the atlas, platform, and vendor investments already committed. You will partner with digital pathology and image-analysis colleagues on H&E whole-slide analysis; deep prior digital pathology experience is welcome but not required.
- AI-enabled translational science. This is an explicit mandate of the role, not a side project. Design and deploy AI approaches for evidence integration and hypothesis generation across patient omics, genetic evidence, perturbation data, and the literature, including LLM-based extraction, agentic and multi-step workflows, and emerging biological foundation models. Given strategic direction, you will have the autonomy to scope, build, and deploy the methods that become the team's translational decision infrastructure. You should not just run existing tools; we want someone who sees what is missing from current approaches and builds it.
- Reusable methods and automation. Build reproducible workflows and cloud-ready pipelines for multimodal data (single-cell, CRISPR and Perturb-seq screens, spatial), so capability persists as a team asset rather than as one-off analyses.
- Scientific influence. Mentor junior scientists and interns, document methods to publication-quality standards, and help raise the computational maturity of the broader translational organization.
Basic Qualifications- Ph.D. in computational biology, bioinformatics, biostatistics, statistics, human genetics, computer science, or a related quantitative field, with 4+ years of relevant academic and/or industry experience;
- Or Master's Degree with 6+ years;
- Or Bachelor's Degree with 8+ years.
Preferred QualificationsWe do not expect any one candidate to bring all of the following. Depth in several of these areas, combined with the judgment to know which question a program is actually asking, matters more than breadth across all of them.
- Demonstrated experience analyzing, integrating, and interpreting high-dimensional patient-derived molecular data in oncology or another translational disease area.
- Strong programming skills in R and/or Python, with practical experience in reproducible analysis and data visualization.
- Working knowledge of the oncology drug development process, sufficient to anticipate what a program needs at target validation, candidate selection, IND-enabling work, and early clinical development.
- Clear scientific communication and the ability to collaborate effectively with biology, translational medicine, clinical development, statistics, and quantitative science partners.
- Spatial biology: hands-on experience with spatial transcriptomics (e.g., Xenium, Visium, Visium HD, CosMx) and/or spatial proteomics and multiplex immunofluorescence (e.g., COMET, PhenoCycler), including cell segmentation, phenotyping, and neighborhood or spatial statistics; familiarity with the analysis stack (Squidpy, SpatialData, scverse) and with digital pathology tooling (HALO, QuPath).
- Prior experience in oncology drug development at a biopharmaceutical company, in translational sciences, discovery, or early clinical development.
- Experience with biomarker strategy, patient selection, pharmacodynamic readouts, companion diagnostic (CDx) development, or clinical translational data interpretation.
- AI and machine learning applied to translational problems: LLM-based evidence and literature extraction, agentic or multi-step analytical workflows, biological foundation models, or multimodal representation learning.
- Causal and driver inference, regulatory network analysis, or other approaches that nominate and prioritize targets from patient molecular data.
- Perturbation biology and functional genomics: CRISPR screens, Perturb-seq, and genetic validation in patient-derived model systems, including integrating perturbation readouts against patient data.
- Cell-type inference and gene-expression deconvolution from bulk, single-cell, and spatial data.
- Reproducible engineering practice: workflow managers (e.g., Nextflow, Snakemake), version control (Git), high-performance computing, and cloud platforms.
- A record of methods development evidenced by peer-reviewed publications and, ideally, released open-source tools or packages.
- A collaborative problem-solver who can operate in ambiguous program settings and translate complex computational output into practical recommendations.
We hire for skills and capabilities, not just credentials - if this role excites you, but doesn't perfectly match your resume, we encourage you to apply anyway.
Compensation Overview:Cambridge Crossing: $166,770 - $202,086
The starting pay range(s) listed above is for full-time employees (FTE). You may also be eligible for additional discretionary incentive cash and stock opportunities. We determine starting pay thoughtfully - carefully considering the nature of the role, required skills, work location, schedule and the knowledge and experience you bring. Final compensation is guided by pay equity principles and applicable employment laws. Compensation programs are reviewed on an ongoing basis and may be adjusted over time to reflect evolving market factors, and individual, team or Company performance.
Benefits:Subject to the terms and conditions of the applicable plans then in effect, you may be eligible to participate in our comprehensive benefit plans - including wellbeing support, retirement and financial protection benefits, and insurance offerings (medical, dental, vision, life and disability).
U.S.-based exempt employees are eligible for Flexible Time Off (FTO), which provides paid time off without a set accrual limit, subject to manager approval, along with 11 paid company holidays each year.
Non-exempt employees, RayzeBio employees, and employees located in Puerto Rico receive 160 hours of paid vacation annually for new hires (subject to manager approval), 11 paid company holidays, and 3 optional holidays.
Depending on eligibility, employees may also have access to additional time-off benefits, including paid sick leave, up to two paid volunteer days per year, summer hours flexibility, and leaves of absence for medical, personal, parental, caregiver, bereavement, or military needs. Eligible employees also enjoy an annual Global Shutdown between Christmas Day and New Year's Day.
U.S.-based job seekers can explore full benefit offerings at https://careers.bms.com/benefits
How We WorkWhere you work matters - because collaboration, innovation and patient impact happen in many settings. Our roles are structured across four work models: site-essential, site-by-design, field-based and remote-by-design. The model assigned to this role is based on its core responsibilities. Learn more at https://careers.bms.com/ways-of-working.
