Cyber Security Researcher
AI Security Institute (AISI)London, UK
AI safety & policy
Information security
Full-time
AI safety & policy
Information security
Full-time
Deadline
2026-11-30
Routes to impact
Direct high impact on an important cause
Description
Build environments, challenges and evaluation infrastructure to benchmark the cyber capabilities of frontier AI systems on real-world security tasks.
- Design cyber ranges and CTF-style challenges to test AI performance on cybersecurity tasks
- Equip evaluation environments with packet capture, penetration testing and reverse engineering tools
- Design metrics and improve automated grading, scoring and evaluation methods
- Write reports, papers and blogs on findings for technical and non-technical audiences
- Fixed-term contract of 24 months
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



