Researcher, Interpretability at OpenAI (San Francisco)
Job Description
OpenAI’s Interpretability team is hiring a researcher to study what goes on inside deep networks, using internal representations to explain model behaviour and to design models whose representations are easier to understand. The goal is safety: keeping future models safe as they grow more capable. The team describes its style as collaborative and curiosity-driven.
At a glance
- Team: Interpretability
- Location: San Francisco
- Pay: $380,000 – $500,000 a year plus equity, as listed
- Apply: open until filled (re-checked 14 October 2026)
What you would do
- Develop and publish research on techniques for understanding the representations inside deep networks
- Build infrastructure to study model internals at scale
- Collaborate across OpenAI on projects it is uniquely placed to pursue
- Steer research towards results that are useful in practice or scale over the long term
Why this role matters
Mechanistic interpretability tries to read what a neural network has learned by looking at its internal representations, rather than only testing its outputs. It is one of the most active areas of AI safety research, and results from frontier labs often shape the field. The role combines publishable research with engineering tools that let the team inspect very large models.
What OpenAI is looking for
- A Ph.D. or research experience in computer science, machine learning or a related field
- Experience in AI safety, mechanistic interpretability or closely related work
- Strong engineering and quantitative reasoning skills
- Interest in long-term AI safety and technical paths to safe AI
Nice to have
- Experience working with very large AI systems
Pay and location
OpenAI lists $380,000 to $500,000 a year plus equity for this San Francisco role.
How to apply
Apply through the official OpenAI job posting. OpenAI’s posting does not give a closing date, so the role is open until filled; ResearchJobs.in will re-check this listing on 14 October 2026. Check the posting for location and work-authorisation details before you apply.
See all our artificial intelligence jobs, or browse more research jobs on ResearchJobs.in.
Hiring institution: OpenAI
Official advertisement: jobs.ashbyhq.com
How to prepare for this application
- Show mechanistic work: circuits, probing, sparse autoencoders or similar projects you ran.
- Publications or write-ups: interpretability blog posts and papers both count.
- Infrastructure: tools you built to inspect models at scale are valued.
- Explain the safety link: say why your research matters for safer models.
About OpenAI
OpenAI is an AI research and deployment company behind the GPT and o-series models, ChatGPT, Codex and the OpenAI API. Its research teams work on training, reasoning, alignment, safety and evaluation of frontier models, mostly from San Francisco.
