OpenAI
Researcher, Frontier Risk Mitigations
$380K–$500K
San Francisco +1 · Full-time · Posted Aug 10, 2026
- Location
- San Francisco
London, UK - Experience
- 2+ years in AI safety and 4+ years of research engineering experience.
- Education
- Ph.D. or other degree in computer science, machine learning, or a related field.
About the job
Research and develop safety mitigations, evaluations, and red-teaming methods to identify and reduce risks in frontier AI systems.
What you'll do
- Identify emerging AI safety risks and develop methods to explore and mitigate them.
- Build and refine evaluations of safety risks, working with domain experts as needed.
- Set safety research directions and develop best practices and red-teaming pipelines.
What they ask for
- 2+ years of experience in AI safety.
- Ph.D. or other degree in computer science, machine learning, or a related field.
- 4+ years of research engineering experience.
- Proficiency in Python or similar languages.
Pay
$380K – $500K USD base salary
Tools
Python, RLHF
AI focus
Developing safety mitigations for frontier AI, including risk evaluation and work involving interpretability, robustness, alignment, and control.
Model-written summary · the original posting is authoritative