AI Red Team Engineer — Adversarial Monitor Security

COL Limited; Greater London; On-site; GBP 122,000 - 160,000; Full time

Benefits offered by this job

Flexible hours

Unlimited vacation

Unlimited sick leave

Parental leave (up to 6 months)

Health, dental and vision insurance

Retirement matching

Meals provided

Paid travel and conferences

Professional development budget

Relocation and visa support

Job summary

COL Limited is seeking an AI Red Team Engineer to lead red-teaming of monitoring systems and frontier labs. You will design campaigns, identify new attack surfaces, and build scalable automated pipelines to strengthen AI monitors.

You will publish findings and translate them into concrete improvements for Watcher and related projects. You will join a small team, shape the tech, and grow into responsibility quickly, working closely with the CEO and engineers across products and monitoring

Qualifications

• Must have 2+ years in offensive security, adversarial ML, or red-teaming of AI systems.
• Strong experience with AI coding agents and frontier monitoring.
• Experience designing and executing structured adversarial testing campaigns.
• Strong Python programming skills.
• Clear, credible external publications and write-ups expected.

Responsibilities

• Design and run red-teaming campaigns combining failure-mode injection into real trajectories and benchmarks.
• Identify novel attack surfaces that monitors haven’t been tested against.
• Build and maintain automated red-teaming pipelines that attack monitors at scale.
• Design iterative adversarial red-team/blue-team games with escalating difficulty.
• Track literature and incidents on agent failure modes and adversarial robustness.
• Turn campaigns into actionable recommendations for monitor developers.

Skills

Offensive security

Adversarial ML

Red-teaming AI

Python

Communication

AI agents

Job description

COL Limited is seeking an AI Red Team Engineer to lead red-teaming of monitoring systems and frontier labs. You will design campaigns, identify new attack surfaces, and build scalable automated pipelines to strengthen AI monitors.

You will publish findings and translate them into concrete improvements for Watcher and related projects. You will join a small team, shape the tech, and grow into responsibility quickly, working closely with the CEO and engineers across products and monitoring