Agrim Bari

About

I am a researcher at M365 Research (Efficient AI), where my work focuses on building efficient systems for machine learning and large language model (LLM) workloads. I am particularly interested in LLM inference and serving, including scheduling, resource management, and systems challenges arising from increasingly long-running and agentic workloads. More broadly, my research interests lie at the intersection of machine learning systems, optimization, and resource allocation.

Prior to joining Microsoft, I completed my Ph.D. in Electrical and Computer Engineering at The University of Texas at Austin (opens in new tab), where I was advised by Prof. Gustavo de Veciana (opens in new tab). At UT Austin, I was part of the Decision, Information, and Communication Engineering (DICE) track and was affiliated with the Wireless Networking and Communications Group (opens in new tab) and the 6G@UT initiative. My doctoral work developed my interest in using optimization and systems thinking to understand and improve complex computing systems.

My broader goal is to build efficient and scalable systems that can support the evolving demands of AI workloads.