jobs

Researcher, Frontier Risk Mitigations

About the TeamModels are becoming increasingly capable—moving from tools that assist humans to agents that can plan, execute, and adapt in the real world. Mitigating the frontier risks resulting from these capabilities is paramount to OpenA

In inglese

Company

OpenAI

Location

San Francisco; London, UK

Status

Open

Posted

2026-08-10T03:31:03.213+00:00

OpenAI's Preparedness team is hiring researchers to work on frontier risk mitigations in San Francisco or London. The role centres on identifying emerging AI safety risks, building and refining evaluations for them, designing red-teaming pipelines, and setting research directions for safer, more aligned models, working alongside experts in misalignment, cybersecurity and biology. The posting asks for a PhD in computer science or machine learning, two or more years in AI safety, four or more years of research engineering, and proficiency in Python.