Kai Huang
AI Frameworks Engineer at Intel Corporation
Minhang District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolKai Huang is an AI Frameworks Engineer with nine years of experience building distributed deep learning systems and production AI pipelines, currently focused on scaling models on Apache Spark at Intel. A first-class Computer Science graduate from the University of Hong Kong with an exchange at Waterloo in Math & CS, he has guided end-to-end solutions for major customers (MasterCard, Microsoft Azure, Tencent, Burger King) and presented on topics from Ray-on-Spark to real-time recommendation systems. Kai contributes to open-source documentation for high-profile projects like Intel’s ipex-llm and BigDL, improving developer usability with cluster tutorials and API guides for LLM components. He combines backend and web-app experience from earlier roles with a knack for teaching and volunteering, often translating complex distributed AI concepts into practical demos and talks. Outside engineering he pursues creative interests—street dance, photography and fashion—which inform his unconventional, user-centered approach to problem solving.
9 years of coding experience
Bachelor of Engineering (B.Eng.), Computer Science, First Class Honours, Bachelor of Engineering (B.Eng.), Computer Science, First Class Honours at University of Hong KongHigh School Diploma, Science, High School Diploma, Science at Shanghai High SchoolExchange, Mathematics and Computer Science, 95.5/100, Exchange, Mathematics and Computer Science, 95.5/100 at University of Waterloo
putonghua, English, Chinese, Shanghainese
Github Skills (8)
rs10
restructuredtext10
sphinx10
documentation10
llm9
gpu9
transformers9
pytorch9
Programming languages (7)
Github contributions (5)
intel/ipex-llm
Sep 2017 - Jan 2023
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, 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, GraphRAG, DeepSpeed, Axolotl, etc
Role in this project:
Technical Writer
Technical WriterContributions:2169 reviews, 1970 commits, 1061 PRs in 5 years 4 months
Contributions summary:Kai's contributions primarily focused on enhancing the documentation of the Orca framework within the ipex-llm repository. This included adding tutorials for YARN and Kubernetes clusters, polishing existing documentation, and updating quick links. The user also incorporated API documentation for LLM components and revised the documentation structure, suggesting a focus on improving usability and clarity for developers.
llm-inferencellama2pythonfinetuningllama
hkvision/bigdl-demo
May 2022 - Dec 2022
Demo of using BigDL Orca
Contributions:39 commits, 4 PRs, 38 pushes in 7 months
bigdlorca
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.