About Me
I am a tenure-track Assistant Professor in the Department of Mathematics, Statistics and Computer Science at the University of Wisconsin–Stout.
My research focuses on distributed and machine learning systems, large language model inference and serving, edge computing, and performance optimization for real-time AI. I earned my Ph.D. in Computer Science from the University of Virginia in December 2024, advised by Prof. Haiying Shen.
My work develops efficient, reliable, and resource-aware systems for machine learning training and inference across heterogeneous edge, cloud, and accelerator platforms. My recent research includes SLO-aware LLM serving, KV-cache management, distributed deep learning, fault tolerance, and low-cost edge inference.
Research Areas
LLM Inference & Serving Distributed ML Systems Edge Computing Performance Optimization Fault-Tolerant AI Adversarial ML
Current Appointment
Tenure-Track Assistant Professor
Department of Mathematics, Statistics and Computer Science
University of Wisconsin–Stout · Fall 2026
Recent Highlights
- Our paper has been accepted to the Applied Research Track of ACM CIKM 2026.
- Two forthcoming 2026 papers on multi-resource-aware LLM serving and KV-cache management.
- Flex, a heterogeneous-accelerator DNN inference system, appeared at EuroSys 2025.
- Publications span EuroSys, SIGCOMM, ICDCS, ICPP, MASS, ICCCN, and related venues.
- Prior research experience at Microsoft, IBM, and the University of Virginia.