Jobs

Anthropic is seeking Research Engineers to join their team and build robust evaluations for their AI system, Claude. In this role, you will transform ambiguous notions of "intelligence" into clear, defensible metrics, designing and implementing evaluations across Claude's full capabilities. You will also build and harden the distributed infrastructure to run these evaluations reliably at scale, partnering closely with researchers to define, run, and interpret results. The ideal candidate will have strong Python skills, experience with distributed systems, and a commitment to steering powerful AI to be safe and beneficial. This position aims to make Anthropic a leader in well-characterized AI systems through exhaustive measurement and validation.