Researcher, Alignment CoT Monitorability

About this role

About the Team The CoT Monitorability team at OpenAI studies whether and when the chain-of-thought of frontier reasoning models is monitorable enough to support scalable oversight. We study how to measure monitorability , which training mechanisms affect monitorability, and speculative methods to improve monitorability. While we mostly focus on CoT monitorability at the moment, we care more generally about any form of monitorability, auditing methods, and improving alignment.…

This is a short excerpt. The full job description and the application are on OpenAI's own site.

More roles at OpenAI

• RTL Design Engineer, Networking / NoCOpenAI · San Francisco
• Principal Software Engineer, Full Stack — CodexOpenAI · San Francisco
• Principal Software Engineer, Full Stack — CodexOpenAI · San Francisco
• Program Manager, M&A Recruiting | PeopleOpenAI · San Francisco
• Program Manager, M&A Recruiting | PeopleOpenAI · San Francisco

Similar roles

• Software Engineer, ML PlatformCursor · Palo Alto, CA
• Software Engineer, ML PlatformCursor · Palo Alto, CA
• Staff Software Engineer, AI Developer ProductivityCoinbase · Remote - USA
• Staff Software Engineer, AI Developer ProductivityCoinbase · Remote - USA
• AI Programmer InternEpicgames · Cary,North Carolina,United States