Expression of Interest: Next-generation Agentic Controls and Forensics (Technical Roles)
UK AI Security Institute · London, UK · London
CHECKED 19H AGO
Research instituteonsite$86k–$192k
At a glance
Highlights
- Build technical foundations for agentic controls and forensics for future AI systems.
- Shape how frontier AI is governed and deployed globally from inside government.
- Get pre-release access to frontier models with ample compute to ship quickly.
What they offer
- Pre-release access to frontier models and ample compute
- At least 25 days annual leave plus 8 public holidays and volunteering days
- 28.97% employer pension contribution and generous parental leave
- Learning stipends, conference funding and freedom to publish
Ideal candidate
Hands-on AI researcher or engineer excited by AI safety who has bold, scalable ideas for detecting misbehaviour in future highly capable agents and wants public-interest impact.
Requirements
- Hands-on AI research experience
- Ideas for scalable approaches to understand misbehaviour from future highly capable AI agents
- Interest in building technical foundations for agentic controls and forensics
- remote policy
- Hybrid working with flexibility for occasional remote work abroad
- visa sponsorship
- Open to applicants of any nationality
- hiring process
- Expression of interest; talent team reaches out if a matching role arises, followed by 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