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 […] 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.
The deadline for applying to this role is Wednesday 25th November 2026, end of day (UK Time).
About the team
As the models we test get more capable and the environments we run them in get more sensitive, we have to continue to be able to run evaluations of highly capable models under proper control and ensure that it remains governed well. Building that governance and keeping it fast is what lets […] keep pace with the work in front of it.
The Security Engineering team keeps […]'s research platform, evaluation environments, and sensitive data secure, and runs the governance, risk, and compliance around them. We harden the environments evaluations run in, detect and respond to threats, and build the controls that let evaluations of highly capable models proceed safely. We work with research teams across […], with partners in frontier AI companies and government.