Research Program Manager – Adversarial Model Research
San Francisco • FullTime
Posted 7mo ago
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
The Human Data team at OpenAI is focused on ensuring the safety and reliability of advanced AI systems. As a Research Program Manager, you will lead critical initiatives to test and evaluate OpenAI's models, identifying vulnerabilities and potential risks through creative experimentation. You will translate complex, ambiguous risks into structured research programs, collaborating closely with research and engineering teams to influence the development and deployment of future AI models. This role requires a technically adept individual who is comfortable with uncertainty and passionate about shaping the future of safe AI.
Responsibilities
- Lead programs exploring unexpected model behaviors and identifying failure modes.
- Translate risk signals into clear priorities and actionable research plans.
- Design and execute creative evaluations, experiments, and red-teaming campaigns.
- Collaborate with research, product, and deployment teams to integrate findings into model development.
- Develop systems for tracking model performance and understanding emerging behavior patterns.
Requirements
- Strong experience in technical program management.
- Excellent organizational and communication skills.
- Familiarity with large language models, prompt engineering, or model evaluation techniques.
- Comfort managing fast-paced, high-uncertainty projects.
- Creativity and resourcefulness in devising new testing methods.
- Ability to coordinate effectively across technical and non-technical stakeholders.
Benefits
- Hybrid work model (3 days in office per week).
- Relocation assistance for new employees.