Jinheng Li

MLSys engineer · software developer · researcher

Ph.D. Student · MBZUAI · Aug 2026 – Present

I work on system optimization, distributed systems, and efficient software at scale — currently focused on LLM serving optimization and high-performance computing.

I am a Ph.D. student at MBZUAI. I optimize large language model serving through frameworks like vLLM, working on memory management, distributed inference, and system-level optimization.

MLSys
Efficiency and scalability of machine learning systems
Operating Systems
Memory management and resource allocation
Distributed Systems
Large-scale system design and optimization
Compilers
Code generation and optimization techniques

Away from the keyboard: photography, the markets, and time with dogs.

Mohamed bin Zayed University of Artificial IntelligencePhD Aug 2026 – Present
University of Texas at AustinMSc 2022 – 2025 · Part-time
City University of Hong KongMPhil 2019 – 2022
Sichuan UniversityBEng 2015 – 2019
Mohamed bin Zayed University of Artificial Intelligence Visiting Researcher · Jun – Aug 2026 · Abu Dhabi
Manpower AI Infrastructure Engineer · 2024 – 2026 · Hong Kong
Microsoft Software Engineer · 2022 – 2024 · Suzhou
Intel Firmware Engineer (Intern) · 2021 – 2022 · Shanghai
Independent iOS Developer Paintoday · 2025 – Present
2026
2024
2023
Shared Dictionary Compression for Efficient Mobile Software Distribution
J. Li, Q. Li, H. Wan, C. J. Xue
IEEE 29th International Conference on Real-Time Computing Systems and Applications (RTCSA), 2023
2020
Acclaim: Adaptive Memory Reclaim to Improve User Experience in Android Systems
Y. Liang, J. Li, R. Ausavarungnirun, R. Pan, L. Shi, T.-W. Kuo, C. J. Xue
USENIX Annual Technical Conference (ATC), 2020
Differentiating Cache Files for Fine-grain Management to Improve Mobile Performance and Lifetime
Y. Liang, J. Li, X. Chen, R. Ausavarungnirun, R. Pan, T.-W. Kuo, C. J. Xue
USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage), 2020 — Extended to FAST 2022 as CacheSifter