I’m Agustín Martinez Suñé.

I obtained my Computer Science Ph.D. at the University of Buenos Aires, Argentina, where I developed formal methods for analyzing distributed systems. These methods are grounded in logical-mathematical foundations to provide provable guarantees about their output.

I’m transitioning to a career in AI safety and AI risk reduction. The main question that currently drives my research is: what role can formal verification techniques play in the field of AI safety?