Senior Scientist, AI Computational Structural Biology
About The Position
The Informatics and Predictive Sciences (IPS) department at Bristol Myers Squibb (BMS) is dedicated to pioneering, partnering, and predicting to drive transformative insights for patient benefit. IPS conducts applied computational research across various fields including genomic, structural, and molecular informatics, computational and systems biology, patient selection, translational biomarker research, knowledge science, epidemiology, and machine learning. This work spans the full lifecycle of drug discovery and development across all therapeutic areas at BMS. We collaborate closely with scientific and clinical experts both internally and externally, performing innovative science to empower data-driven decisions for a rich pipeline of next-generation medicines. This role offers a unique opportunity to shape the future of AI-driven drug discovery at BMS, with a direct impact on induced proximity and targeted protein degradation programs. We are seeking a collaborative and highly innovative computational biologist with a strong background in AI co-folding modeling and a deep understanding of protein structures to join our Predictive Structure and Function team. The successful candidate will work alongside scientists in Protein Homeostasis, Computational Sciences, Oncology, and other teams within the IPS department to discover novel target opportunities leveraging protein-protein interactions and apply these learnings to other small and large molecule modalities.
Requirements
- Bachelor's Degree with 7+ years of academic/industry experience OR Master's Degree with 5+ years of academic/industry experience OR PhD with 2+ years of academic/industry experience
- Proven experience developing and deploying AI/ML models in biological or biochemical contexts, with proficiency in deep learning architectures for structural data (GNNs, equivariant neural networks, transformers, diffusion, flow matching) using Python and relevant libraries (PyTorch, JAX, RDKit, ESM/fair-esm, Biopython, etc.).
- Deep expertise in protein-protein interactions, protein folding, and biomolecular complex formation, with hands-on experience in structure prediction and co-folding frameworks (e.g. AlphaFold2, AlphaFold-Multimer, RoseTTAFold2, Boltz, Chai-1, NeuraPlexer, or equivalent).
- Strong problem-solving mindset with the ability to design novel computational approaches for challenging biological questions.
- Experience contributing to or leading collaborative research projects with academic and/or industry partners and ability to translate scientific findings into actionable drug discovery insights.
- Self-motivated with strong organizational skills and the ability to manage multiple projects simultaneously.
- Demonstrated ability to presenting complex methods and results to diverse scientific audiences and author high-quality scientific reports and publications to publishable standard.
Nice To Haves
- Ph.D. in Computational Biology, Bioinformatics, Structural Biology, Computer Science, Chemistry, or a closely related field, with a strong focus on AI/ML applications in drug discovery with 2+ years of post-doctoral experience in developing AI/ML approaches in university, pharma, or biotech settings, focusing on drug discovery.
- Ability to integrate and analyze multimodal datasets—including structural, genomic, and proteomic data—from both public and proprietary sources, with experience developing algorithms to interpret genomics and proteomics data.
- Familiarity with chemoproteomics data for druggability and ligandability assessment is preferred.
- Experience with induced proximity modalities (for example, PROTACs, molecular glues, and bifunctional molecules) is appreciated but not required.
Responsibilities
- Develop AI/ML models to predict structural biomolecular interactions for novel modalities leveraging protein-protein interactions.
- Design innovative AI/ML approaches to predict protein cooperativity, affinity & other biological properties based on structures.
- Develop co-folding models that incorporate structural and non-structural priors using combinations of public and proprietary BMS data.
- Develop AI/ML models that leverage chemoproteomics data contributing to the generation of novel druggability hypotheses for hard-to-drug targets.
- Author scientific reports, and present methods, results, and conclusions to publishable standard.
- Contribute to the planning and execution of collaborative projects with leading academic and commercial research groups worldwide.
Benefits
- Medical, pharmacy, dental, and vision care.
- BMS Well-Being Account, BMS Living Life Better, and Employee Assistance Programs (EAP).
- 401(k) plan, short- and long-term disability, life insurance, accident insurance, supplemental health insurance, business travel protection, personal liability protection, identity theft benefit, legal support, and survivor support.
- Flexible time off (unlimited, with manager approval), 11 paid national holidays (not applicable to employees in Phoenix, AZ, Puerto Rico or Rayzebio employees) for US Exempt Employees.
- 160 hours annual paid vacation for new hires with manager approval, 11 national holidays, and 3 optional holidays for Phoenix, AZ, Puerto Rico and Rayzebio Exempt, Non-Exempt, Hourly Employees.
- Unlimited paid sick time (based on eligibility).
- Up to 2 paid volunteer days per year (based on eligibility).
- Summer hours flexibility (based on eligibility).
- Leaves of absence for medical, personal, parental, caregiver, bereavement, and military needs (based on eligibility).
- Annual Global Shutdown between Christmas and New Years Day.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
