Bristol Myers Squibb is looking to develop new predictive modeling and optimization approaches for biologics discovery and design by applying advanced computational methods to high-dimensional assay data and antibody repertoires to build models that guide molecular invention and development.
Requirements
- Strong foundation in machine learning, with experience in one or more of: sequence modeling, protein property prediction, optimization methods, or generative modeling.
- Proficiency in Python and ML frameworks (e.g., PyTorch, TensorFlow, JAX).
- Experience handling large biological datasets (sequence, assay, or structural data).
- Strong problem-solving skills and a drive to learn new techniques and apply them in a biological context.
- Background knowledge in protein biochemistry, antibody engineering, or structural biology is desirable but not required.
Responsibilities
- Develop and apply machine learning models to predict antibody properties (e.g., binding affinity, expression, stability, developability).
- Contribute to optimization workflows that support molecular engineering and development candidate selection.
- Collaborate with experimental teams to integrate model predictions with assay feedback in rapid design-make-test-learn cycles.
- Work with team members to prototype, benchmark, and document computational pipelines and workflows.
- Present findings in internal discussions, project meetings, and seminars.
Other
- Ph.D. in computer science, machine learning, statistics, computational biology, or related field; or Master’s with 2–3 years of relevant research or industry experience.
- Excellent written and oral communication skills, with the ability to explain technical concepts across disciplines.
- Interest in working in a highly collaborative, team-oriented environment.
- LI-Hybrid
- The starting compensation range(s) for this role are listed above for a full-time employee (FTE) basis.
