Researcher, Recursive Self-Improvement Safety

OpenAI
San Francisco
Workplace: OnsiteFull timeUSD 295,000 - 445,000 annuallyFunction: Research & Scientific (R&D)Skills: ["Strategic thinking","Research taste","Prioritization","Clear communication","Collaboration"]

Work with Preparedness to anticipate and mitigate loss-of-control and recursive self-improvement risks as frontier AI capability advances. Help build measurements, automated auditing and monitorability approaches, design experiments and evaluations for safety-relevant misalignment, and turn research into institutional safety pipelines. Coordinate verification mechanisms for future safety agreements and strengthen RSI safety cases by identifying mitigation blindspots—moving quickly from prototypes to production-ready practices.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
2 days ago

Researcher, Recursive Self-Improvement Safety

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 21 hours agoStatus: Live
Reposted: similar role first listed 5 months ago

Job Summary

Work with Preparedness to anticipate and mitigate loss-of-control and recursive self-improvement risks as frontier AI capability advances. Help build measurements, automated auditing and monitorability approaches, design experiments and evaluations for safety-relevant misalignment, and turn research into institutional safety pipelines. Coordinate verification mechanisms for future safety agreements and strengthen RSI safety cases by identifying mitigation blindspots—moving quickly from prototypes to production-ready practices.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Consider future OpenAI safety problems and how to prepare for them.
  • •Translate open-ended objectives into concrete, actionable technical directions (e.g., stress-testing monitors for specific threats).
  • •Execute quickly with scrappy prototypes, iterating until work becomes established components of safety pipelines.
  • •Communicate work clearly and secure buy-in from other staff when necessary.
  • •Collaborate with or manage other staff as needed to rapidly scale safety efforts.

Pay and Benefits

Salary: USD 295,000 - 445,000 annually
Equity and Bonus:Equity

Key Requirements

  • •Be an exceptional technical executor who can operate effectively in open-ended, high-uncertainty problem spaces.
  • •Demonstrate strong strategic and research taste to prioritize work in domains with weak feedback loops.
  • •Be passionate about mitigating risks associated with recursive self-improvement.
  • •Communicate your work clearly and secure buy-in from other staff when needed.
  • •Bonus: have prior experience in one or more domains such as ML research, AI alignment, or AI verification.
Experience:AI alignmentML researchAI verificationRed-teaming
Skills:Strategic thinkingResearch tastePrioritizationClear communicationCollaboration

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