Misuse Red Team - Research Engineer/Research Scientist
UK AI Security Institute · London, UK · London
CHECKED 19H AGO
Research instituteonsitejunior, senior, staff, principal
At a glance
Highlights
- Red-team frontier AI safeguards for dangerous capabilities and misuse.
- Research novel attack vectors and build automated attack tooling.
- Share findings with frontier labs and UK officials to shape policy.
Ideal candidate
Impact-driven researcher or engineer passionate about AI safety who loves probing frontier models, designing clever attacks and defences, and turning insights into real-world safer deployment.
Requirements
- Experience developing and analysing attacks and protections for LLM-based systems
- Strong track record of novel and impactful LLM research and publications
- Must obtain BPSS clearance and preferably be eligible for CTC clearance
- visa sponsorship
- Open to applicants of any nationality or background
- hiring process
- Apply by 30 September 2026; successful candidates undergo criminal record check and BPSS clearance.
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