Researcher, Alignment CoT Monitorability

Role

The role involves designing and running empirical studies to improve the monitorability of chain-of-thought in frontier reasoning models. Candidates need strong empirical ML expertise and experience with model behavior, alignment, or interpretability.

Location: San Francisco
Employment: unspecified
Work pattern: hybrid
Seniority: unspecified

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Ashby feed. Source update: 2026-08-04T23:15:30.874+00:00. Check the employer’s page for the complete description, current availability and application terms.

• jobs.ashbyhq.com/openai/82492010-ea96-449d-9949-b726b1a22616 ↗

OpenAI RESEARCH PROFILE ↗