Researcher, Interpretability

OpenAI
San Francisco
Workplace: OnsiteFull timeUSD 310,000 - 460,000 annuallyFunction: Research & Scientific (R&D)Experience: 2+ yearsEducation: phdSkills: ["Collaboration","Curiosity","Problem-solving"]

Researcher focused on mechanistic interpretability of deep networks, developing and publishing techniques to understand model representations, and building scalable infrastructure to study model internals. Collaborates across teams to pursue safety-centric AI research, guiding directions toward practical usefulness and long-term scalability. Requires strong engineering, quantitative reasoning, and experience with large-scale AI systems to advance OpenAI’s safety goals.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
1 year ago

Researcher, Interpretability

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 15 minutes agoStatus: Live

Job Summary

Researcher focused on mechanistic interpretability of deep networks, developing and publishing techniques to understand model representations, and building scalable infrastructure to study model internals. Collaborates across teams to pursue safety-centric AI research, guiding directions toward practical usefulness and long-term scalability. Requires strong engineering, quantitative reasoning, and experience with large-scale AI systems to advance OpenAI’s safety goals.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Develop and publish research on techniques for understanding representations of deep networks.
  • •Engineer infrastructure for studying model internals at scale.
  • •Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue.
  • •Guide research directions toward demonstrable usefulness and/or long-term scalability.
  • •Engage with AI safety and mechanistic interpretability communities to advance best practices.

Pay and Benefits

Salary: USD 310,000 - 460,000 annually
Equity and Bonus:Equity
Perks:Equity

Key Requirements

  • •2+ years of research engineering experience and proficiency in Python or similar languages
  • •Hold a Ph.D. or have research experience in computer science, machine learning, or a related field
  • •Experience in AI safety, mechanistic interpretability, or related disciplines
  • •Ability to develop and publish research on techniques for understanding representations of deep networks and to engineer infrastructure for studying model internals at scale
  • •Strong collaboration and curiosity, with demonstrated ability to guide research directions toward usefulness and scalability
Experience:2+ yearsAI safetyMachine learningDeep learningInterpretability
Education:PhD / Doctorate
Skills:CollaborationCuriosityProblem-solving
Tech Stack:Python

Company Brief

OpenAI
Develops and deploys advanced generative AI models (including ChatGPT and DALL·E) and AI infrastructure, providing APIs and consumer products to accelerate safe AGI for broad benefit.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Scaleup
Valuation: Hectocorn (USD 100B+)
Funding: Series E+
Headquarters: San Francisco, United States
Founded: 2015
Glassdoor
Glassdoor: 4.4
WebsiteLinkedInGlassdoor