Alignment Red Team - Research Engineer/Research Scientist
UK AI Security Institute · London, UK · London
CHECKED 18H AGO
Research instituteonsitejunior, senior, staff, principal
At a glance
Highlights
- Red-team frontier models to detect deceptive alignment and research sabotage.
- Run pre-deployment evaluations informing labs and UK and allied governments.
- Build open-source tooling for better, more realistic alignment evaluations.
Ideal candidate
Autonomous researcher passionate about AI safety and misalignment, eager to stress-test frontier systems and turn abstract loss-of-control risks into evaluations that guide labs and policy.
Lab profile
About UK AI Security Institute
UK government institute studying advanced AI risks and turning research into protective action.
Known for
- Alignment red-teaming
- Control red-teaming
- Misuse red-teaming
- Cyber and autonomous systems security
Key facts
- Based in the UK
- UK government-backed
- World's largest dedicated advanced AI risk team