Research Scientist, Applied Research

AItoolnavio; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

Chai Discovery in San Francisco seeks research scientists to improve the real-world performance of foundation models for drug discovery. You will design evaluation protocols, plan targeted data generation campaigns, and craft post-training recipes to make models actionable in therapeutic challenges.

You will work closely with pre-training researchers, research engineers, and biology teams to ship results rapidly into real programs and help scientists move medicine forward.

Qualifications

• Published ML research on protein, antibody, or small-molecule modelling.
• Knowledge of protein language, structure prediction, and design models (AlphaFold, RFDiffusion, ProteinMPNN, ESM, etc).
• Strong CS/math/physics background, especially probability, statistics and ML.
• Deep software engineering experience with large codebases.

Responsibilities

• Plan targeted data generation campaigns and design evals to measure model performance.
• Develop post-training recipes to make models useful for real drug discovery problems and ship results quickly.

Skills

Protein ML research

Protein language & design

Quantitative background

Large codebases

Tools

AlphaFold

ESM

ProteinMPNN

Job description

About Chai Discovery

Chai Discovery builds the computer-aided design suite for molecules. Eli Lilly, GSK, Pfizer, Bristol Myers Squibb, argenx and Novartis all use Chai to power drug discovery programs. AI is reinventing life sciences the same way it reinvented software engineering, and our team is building that future.

We train frontier models that learn the underlying foundations of biochemical structure and interaction. We pair this with a computational workspace to iterate on molecules from idea to medicine, helping scientists move faster and develop medicines beyond the reach of existing methods.

We value diverse perspectives and are ready to find greatness in unexpected places.

About the role

We are hiring research scientists to improve the real-world performance of our foundation models. The work involves planning targeted data generation campaigns, designing evals that accurately measure model performance, and formulating post-training recipes aimed at making models useful for real drug discovery problems.

We prioritize simple, robust methods over intricate solutions built for narrow problems. We particularly value researchers who can formalize messy biological problems using methods from other fields.

You will work in tight loops with our pre-training researchers, research engineers and science team. Your work will ship fast and you'll see your results reach real therapeutic programs across industry.

About you

We look for technical depth paired with interest in the underlying biology. Biological background is not required. All of the following are positive signals:

• Published research in machine learning for protein, antibody, or small-molecule modelling.
• Fluency in the technical details of protein language, structure prediction, and design models (AlphaFold, RFDiffusion, ProteinMPNN, ESM, etc).
• Strong quantitative background (CS, math, or physics), particularly in probability, statistics, and machine learning.
• Deep software engineering expertise, with experience working in large codebases.

We are happy to bet on rising talent.

We offer

The opportunity to work at the vanguard of AI research and frontier biology, with world-class people, on a mission that matters. We protect and promote a culture of high velocity and ownership. We compensate our team accordingly.