Dingsen Shi

Dingsen Shi is a Ph.D. student in Computer Science and Engineering at the University of North Texas, focusing on storage systems, AI infrastructure, and hardware/software co-design for LLM serving. His research explores how emerging AI workloads interact with the storage stack, including KV-cache management, SSD offloading, NVMe-based data movement, and system-level performance characterization. He has industry experience in storage and chip architecture, with work spanning NVMe SSD systems, computational storage, PCIe/NVMe data paths, and accelerator-oriented system design. His current research investigates how LLM KV-cache offloading behaves at the block-device layer and how future storage systems can be redesigned to better support AI inference workloads.