# Model Policy Manager, Agentic Safety at OpenAI

- Company: OpenAI
- What the company does: Backed by Greylock, Insight and Khosla.
- Company website: https://openai.com/
- Type: Startups (AI role)
- Level: Senior
- Location: San Francisco
- Work setup: Remote
- Pay: $207K to $335K base salary per year (USD)
- Posted: 2026-09-15
- Apply by: 2026-10-30
- Apply: https://jobs.ashbyhq.com/openai/b5a022bb-f7a5-47d9-b5e8-9d1575493dcf
- Page: https://www.1752.vc/careers/jobs/openai-model-policy-manager-agentic-safety/

## About the role

In this role, you will shape how OpenAI understands and addresses real-world risks that emerge from model misalignment as models become more autonomous and operate over longer horizons. You will investigate how misaligned behavior emerges across extended trajectories - including when models persist toward the wrong objective, take unsafe shortcuts, lose track of instructions, exploit weaknesses in their environment, or circumvent constraints - and translate these insights into behavioral policies, evaluations,...

Tags: Safety Systems