Sub Team Lead, Red Team, Control

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.

Risks from misaligned AI systems will grow in importance as AI systems become more capable, autonomous, and integrated into society. AI control measures seek to detect, constrain, and/or counteract potentially misaligned AI models; we expect these measures to become increasingly important in the face of capable AI systems that may be unreliable, deceptive, or misaligned.

The Control Red Team partners with leading frontier AI companies to stress‑test control measures. The team uses techniques from adversarial ML to develop algorithms to find a range of failures in control measures, which are then used to assess and strengthen control measures. These partnerships allow us to directly influence vital control measures, while our position in government lets us bring our understanding of the state of control measures to broader government as they make critical deployment, research, and policy decisions.

We're looking for an experienced researcher to lead the Control sub‑team, driving its research agenda and managing a team of talented research scientists. The ideal candidate combines deep technical expertise in AI control and alignment with the leadership ability to set direction, develop people, and represent the team's work to senior stakeholders inside and outside government.

As Sub Team Lead, you will shape the Control sub‑team's strategy and priorities with the Red Team lead, mentor junior and senior researchers, and serve as a key point of contact with frontier AI labs, UK government officials, and international partners. You'll work closely with the broader Red Team leadership—currently led by Xander Davies and advised by Geoffrey Irving and Yarin Gal—and collaborate with external teams including Redwood Research, Google Deep Mind, Anthropic, and OpenAI.

• Designing, building, running and evaluating methods to automatically attack and evaluate control protocols, such as LLM‑automated attacking and optimisation approaches.
• Building and maintaining infrastructure and benchmarks for AI control experiments, including tools for evaluating the robustness of control measures across diverse threat models.
• Performing adversarial testing of frontier AI system control protocols and producing reports that are impactful and action‑guiding for deployers.

In accordance with the Civil Service Commission rules, the following list contains all selection criteria for the interview process.

The experiences listed below should be interpreted as examples of the expertise we’re looking for, as opposed to a list of everything we expect to find in one applicant:

• Hands‑on research experience with large language models (LLMs) – such as training, fine‑tuning, evaluation, or safety research.
• A demonstrated track record of peer‑reviewed publications in top‑tier ML conferences or journals.
• Ability and experience writing clean, documented research code for machine learning experiments, including experience with ML frameworks like PyTorch or evaluation frameworks like Inspect.
• A sense of mission, urgency, responsibility for success.
• An ability to bring your own research ideas and work in a self‑directed way, while also collaborating effectively and prioritising team efforts over extensive solo work.

• Experience working on AI alignment or AI control.
• Experience working on adversarial robustness, other areas of AI security, or red teaming against any kind of system.
• Extensive experience writing production‑quality code.
• Desire…