Red Team Specialist - Cyber

OpenAI
San Francisco, Seattle
Workplace: HybridFull timeUSD 198,000 - 320,000 annuallyFunction: CybersecuritySkills: ["Communication","Code-building","Attacker mindset","Collaboration","Risk assessment"]

Help secure the responsible deployment of AI by designing and running rigorous evaluations of model cyber capabilities and safeguards. Conduct hands-on, task-specific testing to determine how capable models are when used by experienced security practitioners, and build automated testing infrastructure for repeatable, statistically grounded analysis. Spend additional time testing novel abuse risks in agentic systems and translate findings into risk assessments and actionable recommendations across Security, Research, Product, Policy, and Engineering.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
2 days ago

Red Team Specialist - Cyber

āœ“ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 2 hours agoStatus: Live

Job Summary

Help secure the responsible deployment of AI by designing and running rigorous evaluations of model cyber capabilities and safeguards. Conduct hands-on, task-specific testing to determine how capable models are when used by experienced security practitioners, and build automated testing infrastructure for repeatable, statistically grounded analysis. Spend additional time testing novel abuse risks in agentic systems and translate findings into risk assessments and actionable recommendations across Security, Research, Product, Policy, and Engineering.
Location: San Francisco, Seattle
Workplace: Hybrid
Employment Type: Full time
Job Function: Cybersecurity

Key Responsibilities

  • ā€¢Design and run rigorous evaluations of model cyber capabilities and safeguards, including policy adherence, correct refusal, over-refusal, and resilience to jailbreaking and adversarial techniques.
  • ā€¢Conduct hands-on testing using task-specific harnesses, scaffolding, and multi-step workflows to understand what models enable for experienced security practitioners.
  • ā€¢Distinguish benchmark/policy failures from behaviors that create meaningful real-world risk by evaluating feasibility, attacker uplift, reliability, and existing capabilities elsewhere.
  • ā€¢Build and improve automated testing infrastructure for repeatable measurement, rapid iteration, and statistically grounded analysis across models and product surfaces.
  • ā€¢Test novel abuse risks in agentic systems (e.g., indirect prompt injection and agent hijacking) and translate findings into actionable risk assessments for partners.

Pay and Benefits

Salary: USD 198,000 - 320,000 annually
Equity and Bonus:Equity
Perks:Relocation

Key Requirements

  • ā€¢Deep expertise in cybersecurity (e.g., application security, penetration testing, vulnerability research, adversary simulation, or red-team operations) to assess real-world risk and feasibility.
  • ā€¢Deep expertise in AI model evaluation (e.g., designing and running evals, building agentic harnesses, automating adversarial testing, constructing datasets, or analyzing model behavior at scale).
  • ā€¢Working literacy across both cybersecurity and model evaluation, with interest in developing further depth outside your primary area.
  • ā€¢Ability to write code and build practical testing tools for automating experiments, orchestrating models, or analyzing results.
  • ā€¢Strong written and verbal communication to explain technical findings, limitations, and risk to diverse audiences; experience collaborating with technical and non-technical teams.
Experience:CybersecurityAI model evaluationAdversarial testingAgentic systems
Skills:CommunicationCode-buildingAttacker mindsetCollaborationRisk assessment

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