I am a Research Fellow at the University of Leeds, working at the intersection of computer architecture and system optimization. My work centers on (1) hardware-assisted memory safety, particularly Capability Hardware Enhanced RISC Instructions (CHERI), and (2) systematic optimization techniques for large language models across both training and inference. My research interests include cloud computing, high-performance cluster management, and critical middleware technologies that enable scalable, reliable, and efficient AI systems.

I have served as a TPDS peer reviewer, Eurosys Shadow PC member, and Publicity Co-Chair for IEEE CISOSE JCC, etc.

I am also the founder of ACE3 AI LTD, a spin-out developing a next-generation cloud platform purpose-built for large AI models. The platform equips AI-driven components with a significantly more efficient and cost-effective way to manage and accelerate their workloads, combining an intuitive, user-centric interface with deeply optimized, high-performance execution and scheduling components. This work translates cutting-edge research (Ph.D. dissertation) into practical infrastructure designed for the demands of modern AI development.