Researcher, Agent Safety, Training and Evaluations
OpenAI
San Francisco
More jobs in United States
From the posting
About the Team The Agent Safety team works to ensure that increasingly capable AI agents act safely, exercise sound judgment, and remain aligned with user intent. Our mission is to reduce the probability of severe unintended outcomes from increasingly capable AI agents while preserving their ability to act effectively and autonomously. Our work spans three areas: Training: Create training...
Read the full posting and apply →Posted by OpenAI on its own hiring page. First seen 25 Oct 2026, last confirmed 29 Oct 2026. Details may have changed: check the original before you apply.