Expression of Interest- Chem Bio

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. Expression of Interest – Chem Bio AISI’s Chem Bio team is open to expressions of interest from talented research engineers and scientists of all levels of seniority 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 The Chem Bio team conducts cutting-edge research to understand, evaluate and mitigate chemical and biological risks associated with frontier AI systems. We assess the extent to which advanced models may enable harmful capabilities, develop methods for evaluating these risks rigorously, and share our findings directly with leading AI companies, UK officials and allied governments to inform deployment, research and policy decisions.

Our work spans a range of technical and scientific challenges, including capability elicitation, model evaluations, benchmarking, threat modelling, and the development of safeguards and monitoring approaches. We combine expertise from machine learning, chemistry, biology, biosecurity and related disciplines to better understand how frontier AI systems may affect the chemical and biological risk landscape. We work closely with partners across government, academia and industry, and collaborate with other technical teams across AISI to ensure our work is scientifically rigorous, operationally relevant and decision-useful.

Many of our most impactful projects draw on expertise from across multiple domains, and we actively encourage collaboration in tackling the most pressing challenges in frontier AI safety and security. What you might work on Depending on your background and the needs of the team, you could contribute to work such as: Designing and running evaluations to assess chemical and biological capabilities in frontier AI systems Developing benchmarks, datasets and experimental protocols for assessing high-consequence risks Studying how model capabilities may generalise or transfer across scientific domains and task settings Building tools and automated methods for capability elicitation, testing and monitoring Investigating model safeguards and identifying where they may fail or require strengthening Conducting threat modelling and risk analysis to understand realistic pathways to harm Translating technical findings into actionable recommendations for frontier AI companies and government stakeholders Working with external partners in science, security and policy to improve the broader ecosystem’s understanding of chem/bio-related AI risks Who we’re interested in We are interested in hearing from candidates with strong technical, scientific or research backgrounds relevant to the Chem Bio team’s mission.