AI Red Team Engineer
Apollo Research · London & San Francisco
CHECKED 8H AGO
Research instituteonsite
At a glance
Highlights
- Own red-teaming for AI monitors, including Watcher's own defenses.
- Hunt untested monitor attack surfaces and turn findings into fixes.
- Red-team frontier labs' monitoring systems like Anthropic's auto mode.
Ideal candidate
Attacker-minded builder who loves finding flaws in AI systems and seeing fixes ship. Excited by AI safety at scale and shaping a new practice in a small, fast-moving team.
Lab profile
About Apollo Research
AI safety organisation detecting and mitigating scheming in frontier AI systems and coding agents.
What they build
- Watcher – coding agent security monitoring product
Known for
- Pre-deployment testing with frontier AI labs
- Scheming detection evaluations
- Science of scheming and mitigations research
- Production monitoring of billions of agent tokens monthly