Antonia Marsac

Oversees research operations, fellowship coordination, and strategic partnerships.
Ensures the Lab's work translates into impact across research, policy, and the broader AI safety community.

Lacramioara Corcodel

Specializes in knowledge graph design, network analysis, graph retrieval and graph-based machine learning. Applies these methods to model agent interactions, context propagation and information retrieval.

Laurentiu Meirosu

Specialises in AI systems evaluations, RL training, and multi-agent research. Applies these methods in studying collective intelligence, memory systems and behaviour of  agentic systems. 
 

Konstantin Bernthal

Investigates interaction dynamics, emergent behavior, and failure modes in multi-agent AI systems. Develops theoretical foundations and evaluation frameworks for collective AI safety.