I am a researcher at Queen's University, working with Dr. Bram Adams and Dr. Ahmed E. Hassan at the SAIL Lab. For my Master's and Ph.D., I was at Concordia University in the SPEAR Lab, advised by Dr. Tse-Hsun (Peter) Chen. My current research focuses on LLM agents for software engineering, particularly how they reason, manage context, and whether their outputs can be trusted once applied to real systems. This raises a question for any high-stakes domain: how do we verify what an autonomous agent actually does, when the agent cannot reliably check its own work? I am also broadly interested in software performance engineering and distributed systems.