ML Engineer, Drug Discovery — End-to-End BioAI in SF

Capable; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Generous equity options

Wellness budget

Comprehensive healthcare coverage

HSA, FSA, and 401K access

Daily team dinners

Visa sponsorship where appropriate

Job summary

Capable in San Francisco is seeking a scientist-architect to build machine-learning systems that remove bottlenecks in drug discovery. The role spans research and engineering, identifying valuable problems, adapting biomolecular models, and delivering practical tools for scientists.

You will work closely with wet-lab teams to automate preclinical workflows, connect in silico predictions to in vivo results, and contribute to an environment that rewards ownership, rigor, and rapid iteration.

Qualifications

• Strong research judgment in biomolecular modeling and drug development.
• Ability to own an ambiguous problem end to end.
• Interest in wet-lab realities and building practical tools.
• Curiosity and data-driven approach to create real-world value.
• Experience with active learning or multimodal omics is a plus.

Responsibilities

• Identify high-value bottlenecks where ML can improve speed or decision quality.
• Build systems for experiment planning, literature triage, and candidate generation.
• Fine-tune biomolecular models such as ESM and AlphaFold-family models.
• Develop candidate-analysis workflows including simulations and evaluation.
• Collaborate with wet-lab teams to automate preclinical workflows.
• Create active-learning loops linking in silico predictions to in vivo results.
• Evaluate whether models improve throughput and decision quality.

Skills

Research judgment

End-to-end ownership

Biomolecular modeling

Curiosity & analytical thinking

Active learning experience

Tools

ESM

AlphaFold

RFdiffusion

ProteinMPNN

Job description

Capable in San Francisco is seeking a scientist-architect to build machine-learning systems that remove bottlenecks in drug discovery. The role spans research and engineering, identifying valuable problems, adapting biomolecular models, and delivering practical tools for scientists.

You will work closely with wet-lab teams to automate preclinical workflows, connect in silico predictions to in vivo results, and contribute to an environment that rewards ownership, rigor, and rapid iteration.