Expression of Interest- Red Team in London

About the AI Security Institute

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’re in the heart of the UK government with direct lines to No. 10 (the Prime Minister's office), and we work with frontier developers and governments globally. We’re here because governments are critical for advanced AI going well, and UK AISI is uniquely positioned to mobilise them. With our resources, unique agility and international influence, this is the best place to shape both AI development and government action.

Our Red Team is open to expressions of interest from talented research engineers and scientists who want to work at the forefront of frontier AI safety and security but do not see a role listed that matches their skills and experience. Our talent team will reach out should a role arise that may be a good match.

Team Description

Our Red Team conducts cutting edge research to identify, evaluate and stress test vulnerabilities in frontier AI systems, sharing our findings directly with leading AI companies, UK officials and allied governments to inform deployment, research and policy decisions. The Red Team is composed of three specialised sub teams, each tackling a distinct set of challenges. While each sub team has its own focus, we work closely together, sharing methodologies, tooling, research insights and findings across the wider Red Team. Many of our most impactful projects draw on expertise from across all three sub teams, and we actively encourage collaboration in working to tackle the most pressing challenges in frontier AI safety and security.

Alignment

The Alignment sub-team focuses on detecting, evaluating and understanding misalignment in frontier AI systems. Our work centres on loss of control risks, including deceptive alignment, research sabotage and self-exfiltration attempts. We carry out novel research to develop techniques for finding misalignment, investigate how to attribute misaligned behaviour to more fundamental concerns such as instrumental convergence, and conduct pre and post deployment evaluations. We share our findings with frontier AI companies and with the UK and allied governments to inform deployment, research and policy making, and we work directly with safety teams at frontier labs to help improve their alignment training and monitoring methodologies.

Misuse

The Misuse sub-team focuses on stress testing frontier AI safeguards for dangerous capabilities, researching novel attack vectors and developing advanced automated attack tooling. Our work probes the robustness of safeguards against real world threats, helping to identify where frontier systems may be vulnerable to exploitation and where defences need to be strengthened. We share our findings with frontier AI companies, including Anthropic, OpenAI and DeepMind, as well as with key UK officials and other governments, to inform their deployment, research and policy decisions and to support the development of more resilient safeguards across the frontier AI ecosystem.

Control

The Control sub-team partners with leading frontier AI companies to stress test control measures designed to prevent AI systems from causing harm. Drawing on techniques from adversarial machine learning, we develop algorithms to uncover a wide range of failures in control measures and use these findings to assess and strengthen them. These partnerships allow us to directly influence vital control measures, while our position within government enables us to bring our understanding of the current state of control measures to wider government as critical deployment, research, and policy decisions are made.

Salary

£65,000 - £145,000 GBP

What We Offer

• Impact you couldn't have anywhere else
• Incredibly talented, mission-driven and supportive colleagues.
• Direct influence on how frontier AI is governed and deployed globally.
• Work with the Prime Minister’s AI Advisor and leading AI companies.
• Opportunity to shape the first & best-resourced public-interest research team focused on AI security.

Resources & access

• Pre-release access to multiple frontier models and ample compute.
• Extensive operational support so you can focus on research and ship quickly.
• Work with experts across national security, policy, AI research and adjacent sciences.

Growth & autonomy

• If you’re talented and driven, you’ll own important problems early.
• 5 days off and annual stipends for learning and development, and funding for conferences and external collaborations.
• Freedom to pursue research bets without product pressure.
• Opportunities to publish and collaborate externally.

Life & family

• Modern central London office (cafes, food court, gym), or where applicable, option to work in similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford or Bristol.
• Hybrid working, flexibility for occasional remote work abroad and stipends for work-from-home equipment.
• At least 25 days’ annual leave, 8 public holidays, extra team-wide breaks and 3 days off for volunteering.
• Generous paid parental leave (36 weeks of UK statutory leave shared between parents + 3 extra paid weeks + option for additional unpaid time).
• On top of your salary, we contribute 28.97% of your base salary to your pension.
• Discounts and benefits for cycling to work, donations and retail/gyms.

Salary

Annual salary is benchmarked to role scope and relevant experience. Most offers land between £65,000 and £145,000 made up of a base salary plus a technical allowance (take-home salary = base + technical allowance). An additional 28.97% employer pension contribution is paid on the base salary.

This role sits outside of the DDaT pay framework given the scope of this role requires in depth technical expertise in frontier AI safety, robustness and advanced AI architectures.

Additional Information

Use of AI in Applications

Artificial Intelligence can be a useful tool to support your application, however, all examples and statements provided must be truthful, factually accurate and taken directly from your own experience. Where plagiarism has been identified (presenting the ideas and experiences of others, or generated by artificial intelligence, as your own) applications may be withdrawn and internal candidates may be subject to disciplinary action.

Internal Fraud Database

The Internal Fraud function of the Fraud, Error, Debt and Grants Function at the Cabinet Office processes details of civil servants who have been dismissed for committing internal fraud, or who would have been dismissed had they not resigned. The Cabinet Office receives the details from participating government organisations of civil servants who have been dismissed, or who would have been dismissed had they not resigned, for internal fraud. In instances such as this, civil servants are then banned for 5 years from further employment in the civil service.

Security

Successful candidates must undergo a criminal record check and get baseline personnel security standard (BPSS) clearance before they can be appointed. Additionally, there is a strong preference for eligibility for counter-terrorist check (CTC) clearance. Some roles may require higher levels of clearance, and we will state this by exception in the job advertisement.

Nationality requirements

We may be able to offer roles to applicants from any nationality or background. As such we encourage you to apply even if you do not meet the standard nationality requirements.

Working for the Civil Service

The Civil Service Code sets out the standards of behaviour expected of civil servants. The Civil Service embraces diversity and promotes equal opportunities. As such, we run a Disability Confident Scheme (DCS) for candidates with disabilities who meet the minimum selection criteria.

Diversity and Inclusion

The Civil Service is committed to attract, retain and invest in talent wherever it is found.