Global AI MapJOBS / Anthropic
Research Scientist, Interpretability
San Francisco, CA
Role
This role involves developing methods to reverse-engineer algorithms in large language models and building infrastructure for interpretability experiments. Candidates must have a strong track record in scientific research, enjoy collaborative team science, and be comfortable with messy experimental work.
Location: San Francisco, CA
Employment: full time
Work pattern: hybrid
Seniority: unspecified
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Greenhouse feed. Source update: 2026-10-20T16:52:40-04:00. Check the employer’s page for the complete description, current availability and application terms.