Red Team Technical Governance Researcher

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.

As AI systems become more capable and integrated into the economy, they will increasingly be targeted by adversaries looking to take advantage of their weaknesses.

AISI's Red Team works to understand, evaluate, and improve the technical measures to address these risks ("safeguards"). The team has previously performed pre-deployment tests of leading frontier models [1], and published new datasets [2] and attacks [3].

Our research enables us to develop insights on the safety of frontier systems, which are most impactful when shared.

As a government body, we are well positioned to go beyond technical output and perform research on technical governance relating to safeguards. In this vein, we have already published our Principles for Safeguard Evaluations, which lays out an approach for effective evaluation of frontier AI system safeguards.

There are many more pieces of technical governance research we think are important, such as:

• How can the outputs of safeguard evaluations be made actionable and decision-relevant?

• How can risk from fine-tuning API access be managed effectively?

• What are effective methods for differential or structured access to advanced AI capabilities?

Many of these directions have both a technical component and a governance component, and this role would involve working closely with those performing technical work (and potentially performing technical work yourself) to ensure it is focused on producing actionable insights from a governance perspective.

We're excited for a technical governance researcher to drive forward this work. As these projects draw extensively from the team's broader work and are high priority, this researcher will work closely with the workstream lead and other researchers to reflect the team's prioritisation and experience.

• Ideating, developing and drafting technical governance research on safeguards.
• Reading and understanding in detail relevant research from both within and outside AISI to ensure governance research output is technically informed and grounded.
• Delivering compelling and well-written documents that are received well by relevant stakeholders and audiences.
• Managing multiple stakeholders (both technical and non-technical) involved in producing the research outputs.

You may be a good fit if you have some of the following skills, experience and attitudes:

• Experience working on machine learning, AI, or AI security in industry, in academia, or independently.
• Strong research taste and experience, including ideating new research or technical governance products, executing independently and effectively on completing those produces and delivering them successfully to achieve high impact.
• Extremely strong written and verbal communication skills, both for technical and non-technical communication and audiences.
• Designing, delivering, and maintaining complex written products while managing diverse stakeholders and audiences
• Red‑teaming experience against any sort of system.
• A broad understanding of large language models and the risks surrounding them.
• Ability to work in a self‑directed way with high agency, thriving in a constantly changing environment and a steadily growing team, while figuring out the best and most efficient ways to solve a particular problem.
• Bring your own voice and experience, with an eagerness to support your colleagues, prioritise the team's success, and find new ways of getting things done within government.
• Have a sense of mission, urgency, and responsibility for success, demonstrating…