Mahmoud Kassem

Mahmoud Kassem is a CS and Applied Math student at NYU Abu Dhabi working on LLM code generation evaluation. His research focuses on developing methodologies to detect semantic errors in AI-generated code, ensuring that AI-written scripts verify functionally rather than just compiling correctly. Outside the lab, he is passionate about NLP and AI systems, contributing to open-source language processing tools and working on production deployments of generative AI applications.