Davide Baldelli is a PhD student in Computer Engineering at Polytechnique Montreal and Mila, supervised by Pr. Sarath Chandar and Pr. Amal Zouaq. His current research focuses on AI safety, faithfulness, and introspection capabilities in large language models. Before starting his PhD, he completed an MSc in Artificial Intelligence at the University of Bologna and worked as a machine learning engineer on applied NLP and multimodal ML projects.