Anthropic in San Francisco is seeking an experienced tech lead for the Evals Infrastructure team to build and scale the systems that measure model behavior. You’ll own distributed evaluation pipelines, ensuring fast, reliable, and trustworthy measurements at scale.
You’ll work at the intersection of inference, research, and infrastructure, translating researchers’ needs into robust tooling while guiding a small team and collaborating with cross-functional partners.
#J-18808-Ljbffr