Machine Learning Scientist

BEPC is seeking a Machine Learning Scientist to support computational method development within a cutting-edge therapeutic discovery environment in South San Francisco, CA. This role sits within a Structure and Simulation team focused on advancing biomolecular design and accelerating therapeutic discovery through modern machine learning and scientific computing approaches. The ideal candidate will contribute to developing new ML-driven methodologies and deploy production-ready scientific software to support computational and experimental scientists. Key Responsibilities • Scientific Method Development • Develop new machine learning methodologies for understanding, scoring, ranking, generating, and designing biomolecules (especially proteins) • Build predictive and generative models to prioritize promising molecular designs • Support lab-in-the-loop workflows integrating computational and wet-lab experimentation Software Engineering & Deployment Engineer scalable scientific software and deploy usable workflows Follow best practices in: • Version control • Testing • Modular code development • Documentation • Collaborate within a large shared codebase • Deploy workflows on HPC and cloud platforms • Deliver user-friendly web-based interfaces for medicinal chemists Cross-Functional Collaboration • Partner with computational and experimental scientists • Contribute to advancing biomolecular scientific understanding • Communicate findings clearly to multidisciplinary teams Required Qualifications • BS, MS, or PhD in life sciences, physical sciences, or computational field • Expert-level proficiency in Python • Experience with scientific software development • Experience deploying workflows on HPC and/or cloud platforms • Experience working in collaborative codebases (merge requests, code reviews, writing tests) Understanding of modern machine learning methods, including: • Predictive models • Generative models • Active learning • Strong communication and collaboration skills • Self-starter with high motivation and independence Preferred Qualifications • Public GitHub portfolio • Experience with Rosetta, OpenMM, or computational chemistry tools • 3+ years of industry experience • Experience working with large chemical and biological datasets • Graph-based data • Sequence-based data • Structure-based data Ideal Candidate • Strong ML background applied to molecular design • Comfortable working at the intersection of biology and computation • Production-oriented engineer who values clean, deployable code • Collaborative, yet capable of independent problem-solving • Passionate about advancing therapeutic discovery