Job description

King's College London, Department of Informatics • London, UK

London, UK

In this role, you'll conduct research on mechanism design approaches for aligning advanced AI systems.
Develop theoretical foundations for understanding AI behavior when agents have evolving capabilities.
Apply concepts from game theory and mechanism design to AI alignment challenges.
Collaborate with researchers at King's College London and the UK AI Security Institute.
Explore solution concepts beyond dominant strategies and incentive compatibility for robust AI alignment.

Applications are handled by the employer.

AI Safety Careers does not process applications directly.

Postdoc, Mechanism Design for Robust AI Alignment