Zijie Li
软件工程师 at 华为
New York, New York, China
Summary
🤩
Rockstar🎓
Top SchoolZijie Li is a software engineer with four years of hands-on experience building ML-enabled systems and full-stack applications, currently based in New York and working at Huawei after an AI software internship at Intel. He has practical expertise accelerating local LLM inference and fine-tuning (contributing GPU/CPU/NPU examples and updates for Llama3 and MiniCPM/GLM-4) within Intel’s popular ipex-llm project, bridging research models and production tooling. A NYU Computer Science master’s student, Zijie combines systems-level optimization with application-facing engineering from prior full-stack and IT support roles, making him fluent across the stack and operations. Colleagues find him collaborative and solution-focused; less obvious is his knack for adapting cutting-edge model work to underutilized hardware like Intel NPUs and iGPUs to expand accessible ML deployment options.
4 years of coding experience
1 year of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at New York University美国波士顿大学
Github Skills (8)
transformers10
pytorch10
inference10
gpu10
model-optimization10
llm10
np8
n8
Programming languages (7)
Github contributions (5)
intel/ipex-llm
Jun 2024 - Jan 2025
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.
Role in this project:
ML Engineer
ML EngineerContributions:3 reviews, 31 PRs, 34 comments in 7 months
Contributions summary:Zijie contributed significantly to the implementation and examples of LLM inference and fine-tuning, particularly for MiniCPM and GLM-4 models. Their work included adding GPU and CPU examples, adapting code for NPU, and updating the examples for Llama3.1 and Llama3.2-vision. They demonstrated expertise in integrating models with the IPEX-LLM library.
llm-inferencellama2pythonfinetuningllama
Cecilixy/Kollect_Final_Project
Nov 2022 - Dec 2022
Contributions:44 commits, 26 pushes in 29 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.