Model Policy Manager, Agentic Safety

OpenAI's Model Policy team, part of Safety Systems, works to ensure increasingly capable models behave safely and reliably in real-world environments. In this role you will shape how OpenAI understands and addresses real-world risks from model misalignment as models become more autonomous and operate over longer horizons — including when models persist toward the wrong objective, take unsafe shortcuts, lose track of instructions, exploit weaknesses in their environment, or circumvent constraints. You will translate these insights into behavioral policies, evaluations, monitoring, and safeguards, develop threat models, and identify vulnerabilities that emerge as models interact with tools, data, and external systems. Based in San Francisco, three days per week in office.