Graduated from UCAS, working on large-scale distributed LLM inference.
LLM inference · Serving systems · GPU kernels · Python · Rust
I am interested in the infrastructure behind LLM deployment, deep learning systems, and LLM backend engineering.
- Inference engines and distributed serving
- Compilers, runtimes, and kernel performance
- Systems work around model deployment at scale
| Role | Company | Duration |
|---|---|---|
| LLM Distributed Serving | - | May 2026 – Present |
| LLM Architecture | Enflame | Jan 2025 – Sep 2025 |
| LLM Algorithm | Skywork | Sep 2023 – Apr 2024 |
| Text2Image Training Framework | Turing AI Institute of Nanjing | Jun 2023 – Sep 2023 |
Outside engineering, I am also into anime cosplay.
Email: 213193509seu@gmail.com



