About the Role
The AI Security Institute is seeking talented AI research scientists and engineers interested in building technical foundations for agentic controls and forensics for future AI systems. This role offers the opportunity to influence frontier AI development and global governance, working with leading experts and organizations.
Responsibilities
- Build technical foundations for agentic controls and forensics for future AI systems.
- Translate advanced AI risk knowledge into actionable strategies.
- Collaborate with frontier AI developers and governments globally.
- Work with the Prime Minister’s AI Advisor and leading AI companies.
- Pursue research bets without product pressure.
- Publish and collaborate externally.
Requirements
- Relevant hands-on AI research experience.
- Ideas for approaches that will scale to understanding misbehavior from future generations of highly capable AI agents.
- Must undergo a criminal record check and obtain baseline personnel security standard (BPSS) clearance.
- Strong preference for eligibility for counter-terrorist check (CTC) clearance.
- Must adhere to the Civil Service Code.
- Meet minimum selection criteria for the Disability Confident Scheme (if applicable).
- Meet minimum requirements for the Redeployment Interview Scheme (if applicable).
Skills
- AI research
- AI engineering
- Agentic controls
- Forensics for AI systems
- AI risk analysis
- AI governance
- AI safety
- AI robustness
- Advanced AI architectures
Location
- Central London, UK
- Birmingham, UK
- Cardiff, UK
- Darlington, UK
- Edinburgh, UK
- Salford, UK
- Bristol, UK
Work Type
- Hybrid working
- Occasional remote work abroad
Experience Level
- Mid-level
- Senior-level
Salary/Compensations
- £65,000–£145,000
Benefits
- Pre-release access to frontier models and ample compute.
- Extensive operational support.
- Work with experts across national security, policy, AI research and adjacent sciences.
- 5 days off for learning and development.
- Annual stipends for learning and development.
- Funding for conferences and external collaborations.
- Modern central London office.
- Option to work in similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford or Bristol.
- Flexibility for occasional remote work abroad.
- Stipends for work-from-home equipment.
- At least 25 days’ annual leave.
- 8 public holidays.
- Extra team-wide breaks.
- 3 days off for volunteering.
- Generous paid parental leave (36 weeks shared + 3 extra paid weeks + option for additional unpaid time).
- 28.97% employer pension contribution on base salary.
- Discounts for cycling to work.
- Discounts for donations.
- Discounts for retail.
- Discounts for gyms.
About the Company
- The AI Security Institute is the world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action.
- We are in the heart of the UK government with direct lines to No. 10 (the Prime Minister's office).
- We work with frontier developers and governments globally.
- We are uniquely positioned to mobilise governments for advanced AI.
- We are the best place to shape both AI development and government action.
- We are the first and best-resourced public-interest research team focused on AI security.
Equal Opportunity
- The Civil Service embraces diversity and promotes equal opportunities.
- We run a Disability Confident Scheme (DCS) for candidates with disabilities who meet the minimum selection criteria.
- The Civil Service also offers a Redeployment Interview Scheme to civil servants who are at risk of redundancy, and who meet the minimum requirements for the advertised vacancy.
- We encourage applications from any nationality or background.
- The Civil Service is committed to attract, retain and invest in talent wherever it is found.
