Researcher, Frontier Biological and Chemical Risks

OpenAI
San Francisco
Workplace: OnsiteFull timeUSD 295,000 - 445,000 annuallyFunction: Research & Scientific (R&D)Skills: ["Red-teaming mindset","Cross-functional communication","Project delivery","Critical thinking","Adaptability"]

Own the scientific validity of frontier preparedness capability evaluations by designing new evals grounded in real threat models (including CBRN, cyber, and other frontier-risk areas) and maintaining existing ones to prevent staleness or silent regressions. Define datasets, graders, rubrics, and threshold guidance, and produce auditable artifacts—evaluation cards, capability reports, and system-card inputs. Collaborate on emerging AI safety risk methodologies and scalable evaluation systems in a high-stakes, fast-paced environment.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
2 days ago

Researcher, Frontier Biological and Chemical Risks

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 6 hours agoStatus: Live

Job Summary

Own the scientific validity of frontier preparedness capability evaluations by designing new evals grounded in real threat models (including CBRN, cyber, and other frontier-risk areas) and maintaining existing ones to prevent staleness or silent regressions. Define datasets, graders, rubrics, and threshold guidance, and produce auditable artifacts—evaluation cards, capability reports, and system-card inputs. Collaborate on emerging AI safety risk methodologies and scalable evaluation systems in a high-stakes, fast-paced environment.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Identify emerging AI safety risks and develop new methodologies to explore their impact.
  • •Build and continuously refine evaluations of frontier AI models to assess the extent of identified risks.
  • •Design and build scalable systems and processes supporting these evaluations.
  • •Define datasets, graders, rubrics, and threshold guidance for auditable preparedness capability evaluations.
  • •Contribute to risk management refinement and development of best-practice guidelines for AI safety evaluations.

Pay and Benefits

Salary: USD 295,000 - 445,000 annually
Perks:Equity

Key Requirements

  • •Passion and knowledge about short-term and long-term AI safety risks.
  • •Experience in ML research engineering, ML observability/monitoring, and/or creating large language model-enabled applications, or another technical domain applicable to AI risk.
  • •Ability to operate effectively in a fast-paced research environment and scope/deliver projects end-to-end.
  • •A red-teaming mindset and the ability to think outside the box.
  • •(Great to have) First-hand experience in red-teaming systems and a nuanced understanding of societal aspects of AI deployment.
Experience:AI safetyML researchFrontier AICBRNRed-teaming
Skills:Red-teaming mindsetCross-functional communicationProject deliveryCritical thinkingAdaptability

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