Requirements

2+ years of experience in offensive security, adversarial ML, or red-teaming of AI systems
Strong experience with AI coding agents, including use, comparison, or development of frontier 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
Demonstrated ability to work independently on open-ended adversarial problems

Nice to haves

Design and run red-teaming campaigns combining severity-graded failure-mode injection into real trajectories, static monitoring benchmarks, and dynamic off-policy control red-teaming
Identify novel attack surfaces that monitors haven't been tested against
Build and maintain automated red-teaming pipelines to attack monitors at scale
Design iterative adversarial red-team/blue-team games, collaborating with the RS (Control) team to escalate attack difficulty as monitors improve
Track research literature and real-world incidents on agent failure modes, monitor evasion, and adversarial robustness
Turn campaign results into specific, actionable recommendations for monitor developers
Write up campaign findings as external publications and internal reports
Feed findings back into Watcher's monitor development and Apollo's blue-teaming research to enhance product robustness

Market competitive salary, equity, and comprehensive benefits
Salary ranges: San Francisco $182,000 – $238,000; London £122,000 – £160,000, with plans to raise salaries
Flexible work hours and schedule
Unlimited vacation and sick leave
Up to 6 months paid parental leave
Comprehensive health, dental, and vision insurance
Retirement savings with competitive employer matching (e.g. 401(k) for US employees)
Lunch, dinner, and snacks provided on workdays
Paid work trips including staff retreats, business trips, and relevant conferences
Yearly $1,000 professional development budget
Relocation support and visa fees if applicable