Workstream Lead, Agentic AI Risk Modelling and Mitigations
UK AI Security Institute · London, UK · London
CHECKED 18H AGO
Research instituteonsitesenior
At a glance
Highlights
- Lead scenario-based risk modelling for advanced autonomous AI systems.
- Drive monitoring, deployment guidance and containment mitigations into adoption.
- Inform real government decisions on oversight of difficult-to-control AI.
Ideal candidate
A senior research leader with strong technical judgement and people leadership who cares deeply about AI safety and turning analysis into real-world government action.
- hiring process
- Apply by 13 October 2026; requires criminal record check and BPSS clearance with preference for CTC eligibility.
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