AI Red Team Engineer
Apollo Research2 months ago
London, United Kingdom or San Francisco, CA, USAMid Level
Base Salary
$182k - $238k/yr
Responsibilities
- Design and execute severity-graded red-teaming campaigns against AI monitors using real trajectories, static benchmarks, and dynamic off-policy control red-teaming.
- Identify novel attack surfaces and monitor-evasion methods that have not been tested previously.
- Build and maintain automated red-teaming pipelines that attack monitors at scale.
- Design iterative adversarial red-team/blue-team games with the RS (Control) team.
- Track research literature and real-world incidents involving agent failure modes, monitor evasion, and adversarial robustness.
- Produce actionable recommendations for monitor developers regarding intervention timing, user authorization, trust boundaries, and monitor visibility.
- Write external publications and internal campaign reports.
- Feed red-team findings into Watcher monitor development and Apollo blue-teaming research.
Requirements
- At least 2 years of experience in offensive security, adversarial ML, or AI-system red-teaming.
- Strong experience using, comparing, or directly developing frontier AI coding agents.
- Experience designing and executing structured adversarial testing campaigns.
- Strong Python programming skills.
- Strong written communication skills for clear and credible publications and campaign write-ups.
- Ability to work independently on open-ended adversarial problems.
- Familiarity with AI safety concepts, particularly agent-related risks, is preferred.
- Experience with LLM-as-a-judge systems or AI monitoring is preferred.
- Background in penetration testing, CTFs, or computer security is preferred.
Benefits
- Market-competitive salary, equity, and competitive benefits.
- Flexible work hours and schedule.
- Unlimited vacation and sick leave.
- Up to 6 months of paid parental leave.
- Comprehensive health, dental, and vision insurance.
- Retirement savings with competitive employer matching, including 401(k) for US employees.
- Lunch, dinner, and snacks provided on workdays.
- Paid work trips, staff retreats, business trips, and relevant conferences.
- $1,000 USD yearly professional development budget.
- Relocation support and visa fees if applicable.
- Full-time, in-person role based in the London or San Francisco office with flexible work-from-home arrangements.
- Apollo Research sponsors visas in the UK and US, subject to role and candidate circumstances.
About Apollo Research
Apollo Research evaluates and stress-tests frontier AI models for safety risks and builds security tools for agentic systems used by enterprise engineering teams. It works with OpenAI, Anthropic, Google, Meta and others to run pre-deployment tests focused on deceptive behavior and loss-of-control risks, and sells Watcher, a coding-agent security product that monitors billions of tokens in production. Revenue comes from enterprise software and research partnerships with AI labs and agent-building companies.