Senior Scientist, AI Computational Structural Biology

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.

• Bachelor's Degree
• 7+ years of academic / industry experience
• Or Master's Degree
• 5+ years of academic / industry experience
• Or PhD
• 2+ years of academic / industry experience
• AI/ML & Deep Learning:
  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.).
• Structural Biology and Co-folding:
  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, Alpha Fold-Multimer, RoseTTAFold2, Boltz, Chai-1, Neura Plexer, or equivalent).
• Multi-Omics Data Integration:
  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.
• Chemoproteomics & induced proximity:
  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.
• 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.