Giuseppe Vietri

I am an applied research scientist, based in New York City. I work on synthetic data generation for building high-fidelity, verifiable environments for training and evaluating LLM agents. More recently, I've been interested in formal methods as a path to more reliable LLM systems, constraining inference through formal languages like Lean 4 so that outputs can be verified.

I obtained my Ph.D. in 2023 at the University of Minnesota, Twin-cities in the Computer Science and Engineering Department. I was co-advised by Maria Gini and Steven Wu. Before that, I completed a Master's in Computer Science at Florida International University under Professor Giri Narasimhan.