Global AI MapJOBS / Anthropic
Research Engineer, Post-Training Model Evaluations
San Francisco, CA | Seattle, WA
Role
This role leads the science of evaluating production training runs for Anthropic's Claude models, focusing on observability and model quality. Candidates must have strong Python skills, experience designing and analyzing ML evaluations at scale, and the ability to influence direction across teams.
Location: San Francisco, CA | Seattle, WA
Employment: full time
Work pattern: hybrid
Seniority: senior
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Greenhouse feed. Source update: 2026-09-27T23:35:11-04:00. Check the employer’s page for the complete description, current availability and application terms.