jobs

Researcher, Safety Oversight

About the TeamThe Safety Systems team is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit the society, and is at the forefront of OpenAI's mission to build and deploy safe AGI

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2025-01-28T16:12:01.888+00:00

OpenAI's Safety Oversight Research team is hiring a senior researcher to advance oversight of frontier models. The work covers building AI monitor models that detect misuse and misalignment, setting research directions, designing red-teaming pipelines for end-to-end robustness, and improving how models reason about human values, with cross-functional work alongside trust and safety, legal and policy teams. Requirements: a Ph.D. or related degree, 4+ years in AI safety and in research engineering, and Python proficiency. The distinctive part is setting oversight research directions.