OpenAI
Researcher, Alignment Interpretability
$295K–$500K
San Francisco · Full-time · Posted Sep 1, 2026
- Experience
- 2+ years of research engineering experience.
- Education
- Ph.D. or research experience in computer science, machine learning, or a related field.
About the job
Conduct mechanistic interpretability research to understand deep-network representations and help improve the safety and alignment of powerful AI systems.
What you'll do
- Develop and publish research on techniques for understanding deep-network representations.
- Build infrastructure to study model internals at scale.
- Collaborate across teams and guide research toward demonstrable usefulness or long-term scalability.
What they ask for
- 2+ years of research engineering experience.
- Proficiency in Python or similar languages.
Nice to have
- Experience in AI safety and alignment, mechanistic interpretability, or related disciplines.
- Ph.D. or research experience in computer science, machine learning, or a related field.
Pay
$295K – $500K (base salary); Offers Equity (amount not stated)
Tools
Python
AI focus
Research into model representations and internals to support AI safety and alignment.
Model-written summary · the original posting is authoritative