Research Program Manager – Adversarial Model Research
New roles land in Following.
Job description preview
From OpenAI’s original posting
ABOUT THE TEAM The Human Data team at OpenAI is responsible for identifying and mitigating risks in advanced AI systems by designing evaluations, surfacing vulnerabilities, and collaborating closely with researchers to strengthen model reliability and public trust. ABOUT THE ROLE As a Research Program Manager, you will lead initiatives that test the safety and robustness of OpenAI’s models through creative experimentation and structured evaluation. You’ll coordinate efforts across research and engineering teams to transform ambiguous risks into concrete research programs and influence future model development and deployment. We’re looking for people who are technically savvy, comfortable with ambiguity, and excited about shaping the future of safe AI. This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees. IN THIS ROLE, YOU WILL: - Lead programs that explore unexpected model behaviors and identify failure modes. - Translate vague or emergent risk signals into clear priorities and actionable research plans. - Design and run creative evaluations, experiments, and red-teaming campaigns. -…
Open full posting on OpenAI’s site