Yiwei Jiang
Ph.D. Student, Electrical and Computer Engineering, Cornell University
yj644 AT cornell.edu
I am a first-year Ph.D. student in Electrical and Computer Engineering at Cornell University (Cornell Tech, New York City), advised by Prof. Udit Gupta. I design and optimize GPU-centric machine learning systems through hardware-software co-design, spanning systems, networking, and architecture — with the goal of enabling scalable and sustainable ML platforms.
Before Cornell, I received my M.S. in Computer Sciences from UW–Madison, where I was fortunate to be advised by Prof. Shivaram Venkataraman and Prof. Matt Sinclair. I also worked as a research associate at AMD Research and Advanced Development (RAD), where I was mentored by Dr. Srilatha (Bobbie) Manne on power-efficient LLM inference and GPU workload optimization.
Research Interests
ML Systems · GPU Architecture · Power-Efficient Inference · Hardware-Software Co-Design · Workload Characterization
Research Experience
Continued GPU-centric ML systems research with Prof. Shivaram Venkataraman and Prof. Matt Sinclair.
Enabled prefill/decode disaggregation runtime achieving 20% energy reduction and 2× higher SLO attainment.
Proposed a dual classification scheme for GPU workloads that reduces profiling time by 90% for predicting frequency-capping impact.
Education
Advisor: Udit Gupta
Advisors: Shivaram Venkataraman, Matt Sinclair