Summary
Samuele Poppi is a postdoctoral researcher and applied AI safety specialist with eight years of experience bridging academic research and industry practice. Currently at MBZUAI, he leads student supervision and projects on watermarking, red- and blue-teaming, and broader alignment problems after a Research Scientist internship on GenAI safety at Meta. His PhD work focused on “Responsible AI in Vision and Language,” reflecting a consistent emphasis on ethics, transparency, and robustness across vision-and-language models. Known for switching perspectives when stuck, he combines rigorous academic training (cum laude MS) with hands-on engineering experience in ML/DL roles and research fellowships. Based in Abu Dhabi, he brings a pragmatic mix of project management and technical depth to hard problems in model responsibility that span both blue-team defenses and red-team adversarial thinking.
8 years of coding experience
2 years of employment as a software developer
Master's degree, Computer Engineering, 110 cum laude, Master's degree, Computer Engineering, 110 cum laude at Università degli Studi di Modena e Reggio Emilia
Doctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at Università di Pisa