Researcher, Frontier Risk Mitigations

OpenAI
San Francisco
Workplace: OnsiteFull timeUSD 295,000 - 445,000 annuallyFunction: Research & Scientific (R&D)Experience: 2+ yearsEducation: phdSkills: ["Cross-functional collaboration","Technical depth","Strategic thinking"]

Help derisk frontier AI models by developing novel safety mitigations for deployed systems. Work with the Preparedness team to identify emerging AI safety risks, build and continuously refine evaluations, and set research strategies that improve alignment, robustness, and safety. Collaborate cross-functionally with experts in misalignment, cybersecurity, and biology to design end-to-end safety stacks, including red-teaming pipelines and safety best-practices guidelines.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
1 day ago

Researcher, Frontier Risk Mitigations

āœ“ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 17 hours agoStatus: Live

Job Summary

Help derisk frontier AI models by developing novel safety mitigations for deployed systems. Work with the Preparedness team to identify emerging AI safety risks, build and continuously refine evaluations, and set research strategies that improve alignment, robustness, and safety. Collaborate cross-functionally with experts in misalignment, cybersecurity, and biology to design end-to-end safety stacks, including red-teaming pipelines and safety best-practices guidelines.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • ā€¢Identify emerging AI safety risks and develop new methodologies for exploring and mitigating their impact.
  • ā€¢Build and continuously refine evaluation systems to assess the extent of AI safety risks, with input from domain experts.
  • ā€¢Set research directions and strategies to make AI systems safer, more aligned, and more robust.
  • ā€¢Contribute to AI safety best-practices guidelines for OpenAI and the wider industry.
  • ā€¢Evaluate and design red-teaming pipelines to test end-to-end robustness and identify areas for improvement.

Pay and Benefits

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

Key Requirements

  • ā€¢2+ years of experience in AI safety, including areas like RLHF, human-AI collaboration, interpretability, or control.
  • ā€¢4+ years of research engineering experience and proficiency in Python or similar languages.
  • ā€¢A Ph.D. or other degree in computer science, machine learning, or a related field.
  • ā€¢Strong technical depth and the ability to apply methods from interpretability, robustness, alignment, and control to improve safety.
  • ā€¢Experience working with large-scale AI systems and thriving in fast-paced environments.
Experience:2+ yearsAI safetyMachine learningLarge-scale AI systems
Education:PhD / Doctorate in computer science, machine learning, or a related field
Skills:Cross-functional collaborationTechnical depthStrategic thinking
Tech Stack:Python

Company Brief

OpenAI
Develops and deploys advanced generative AI models (including ChatGPT and DALLĀ·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