AI Red Team Engineer

AI Red Team Engineer Overview

Apollo Research is seeking an AI Red Team Engineer to join our team in either London or San Francisco. This role is integral to the development of Watcher, a monitoring tool designed for coding agents, as we aim to enhance safety at scale through our monitoring research agenda. As the AI Red Team Engineer, you will be responsible for establishing the practice of red-teaming AI monitors, including both Watcher’s defenses and those of frontier labs. You will work closely with our CEO and other researchers to identify vulnerabilities and improve our monitoring systems.

Key Responsibilities

• Design and run red-teaming campaigns that integrate severity-graded failure-mode injections into real trajectories, static monitoring benchmarks, and dynamic off-policy control red-teaming.
• Identify novel attack surfaces that existing monitors have not yet been tested against.
• Build and maintain automated red-teaming pipelines to attack monitors at scale, moving beyond one-off manual probing.
• Design iterative adversarial red-team/blue-team games, collaborating with the blue-team to escalate attack difficulty as monitors improve.
• Track research literature and real-world incidents related to agent failure modes, monitor evasion, and adversarial robustness.
• Convert findings from each campaign into actionable recommendations for monitor developers regarding intervention timing, user authorization, trust boundaries, and monitor visibility.
• Document campaign findings in external publications and internal reports.
• Feed insights back into Watcher’s monitor development and Apollo’s blue-teaming research to enhance our product.

Job Requirements

• At least 2 years of experience in offensive security, adversarial machine learning, or red-teaming AI systems.
• Strong experience with AI coding agents, including extensive use, comparison, or direct development of frontier coding agents.
• Experience in designing and executing structured adversarial testing campaigns.
• Proficient programming skills in Python.
• Strong written communication skills for producing clear and credible publications and campaign reports.
• Ability to work independently on open-ended adversarial problems.

Benefits

• Market competitive salary and equity options.
• Salary range: $182,000 – $238,000 in San Francisco; £122,000 – £160,000 in London, with plans for salary increases.
• Flexible work hours and schedules.
• 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.
• Free lunch, dinner, and snacks on workdays.
• Paid work trips, including staff retreats and conferences.
• A yearly $1,000 professional development budget.
• Relocation support and visa fees assistance if applicable.

Working Pattern

This is a full-time, in-person role based in our London or San Francisco office, with flexible working hours and arrangements available.

Visa Sponsorship

We sponsor visas in both the UK and US. While sponsorship is not guaranteed for every role or candidate, we will work with you to find the appropriate visa route if an offer is made.

About the Team

The product team includes research scientists and product engineers, with guidance from our CEO. You will collaborate with other software engineers and researchers, as we aim to utilize our products internally for research purposes.

About Apollo Research

Apollo Research focuses on the risks associated with AI capabilities, particularly those arising from loss of control. We are dedicated to addressing deceptive alignment and enhancing monitoring systems to mitigate risks. Our culture promotes truth-seeking, goal orientation, and constructive feedback.

How to Apply

Please complete the application form with your CV. A cover letter is not required, but you may share links to relevant work samples. The interview process includes a screening interview, a take-home test, technical interviews, and a final interview with our CEO. We do not conduct traditional coding interviews, and you may use AI tools for the take-home test.

Degree Requirement: Not Specified

Visa Sponsorship Promising