Researcher, Frontier Cybersecurity Risks

OpenAI
San Francisco
Workplace: OnsiteFull timeUSD 295,000 - 445,000 annuallyFunction: CybersecuritySkills: ["Cross-functional collaboration","Technical evaluation","Rigorous testing","Risk-focused problem-solving","Iteration"]

Design and implement an end-to-end mitigation stack to reduce severe cyber misuse across OpenAI products. Work within the Preparedness Safety Research team on prevention, monitoring, detection, and enforcement components, integrating safeguards across product surfaces. Evaluate cybersecurity risk trade-offs across coverage, latency, model utility, and privacy, collaborate with risk/threat modeling partners, and run rigorous testing and red-teaming to stress-test and iterate.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
2 days ago

Researcher, Frontier Cybersecurity Risks

āœ“ 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

Design and implement an end-to-end mitigation stack to reduce severe cyber misuse across OpenAI products. Work within the Preparedness Safety Research team on prevention, monitoring, detection, and enforcement components, integrating safeguards across product surfaces. Evaluate cybersecurity risk trade-offs across coverage, latency, model utility, and privacy, collaborate with risk/threat modeling partners, and run rigorous testing and red-teaming to stress-test and iterate.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Cybersecurity

Key Responsibilities

  • ā€¢Design and implement mitigation components for model-enabled cybersecurity misuse, covering prevention, monitoring, detection, and enforcement.
  • ā€¢Integrate safeguards across product surfaces with product and engineering teams for consistency and low latency at scale.
  • ā€¢Evaluate technical trade-offs across coverage, latency, model utility, and user privacy, proposing pragmatic testable solutions.
  • ā€¢Collaborate with risk and threat modeling partners to align mitigation design with anticipated attacker behaviors and misuse scenarios.
  • ā€¢Execute rigorous testing and red-teaming workflows to stress-test the mitigation stack and iterate based on findings.

Pay and Benefits

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

Key Requirements

  • ā€¢Demonstrated experience in deep learning and transformer models.
  • ā€¢Proficiency with frameworks such as PyTorch or TensorFlow.
  • ā€¢Strong foundation in data structures, algorithms, and software engineering principles.
  • ā€¢Familiarity with training and fine-tuning large language models, including distillation, supervised fine-tuning, and policy optimization.
  • ā€¢Significant experience designing and deploying technical safeguards for abuse prevention, detection, and enforcement at scale.
Experience:AI safetyCybersecurityRed-teamingLarge language models
Skills:Cross-functional collaborationTechnical evaluationRigorous testingRisk-focused problem-solvingIteration
Tech Stack:PyTorchTensorFlowTransformer modelsLarge language modelsLLMs

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