MrAlejandro Mercado

I am a 2nd-year PhD candidate and President’s PhD Scholar at Imperial College London’s Department of Computing, working in the Safe Artificial Intelligence Lab (SAIL), led by Prof. Alessio Lomuscio. My research lies at the intersection of formal methods and agentic systems, with the goal of developing AI agents that are not only safe and reliable by construction, but also capable and practically useful. I am particularly interested in providing formal guarantees for LLM-driven agents that interact with tools, data, and complex environments.

Before joining Imperial, I completed my Licenciatura, a six-year degree equivalent to a combined Bachelor’s and Master’s, in Computer Science at the University of Buenos Aires (UBA). The program at UBA emphasized rigorous training in theoretical computer science, mathematics, and formal logic. My thesis focused on Belief Revision, a subfield of Knowledge Representation and Reasoning and a core area of Symbolic AI, that focuses on handling inconsistencies in knowledge bases. After graduating, I worked at Safe Intelligence, an Imperial spin-off, carrying out a project on the formal verification of object detection models for safety-critical applications.