King's College London is seeking a postdoctoral researcher to join a newly funded project, "The Implementability-Capability Frontier: Mechanism Design for Robust AI Alignment," supported by the UK AI Security Institute and UK Research and Innovation. The research aims to establish theoretical foundations for aligning advanced AI systems using mechanism design, focusing on the guarantees possible when agents are powerful and have evolving capabilities.

The position is ideal for candidates with a PhD in computer science, economics, operations research, or related fields. Applicants should have a strong background in mechanism design, algorithmic game theory, or social choice theory, and a keen interest in applying these theoretical tools to AI alignment challenges. The project will explore topics such as incentive compatibility, solution concepts beyond dominant strategies, and imperfect rationality, all within the context of aligning frontier AI systems.

This opportunity offers the chance to conduct foundational research in a critical area, with the support of a world-class institution and the academic freedom to pursue bold ideas. The team is being built at King's College London, and the successful candidate will work closely with Professor Carmine Ventre, a leading expert in computational finance and mechanism design.

Interested candidates are encouraged to send a direct message to Professor Ventre with their CV and a brief note on their relevant background. A formal call for applications will follow, but early expressions of interest are welcome.