Junwei Deng
Research Intern at University of Illinois Urbana-Champaign
Illinois, United States
Summary
🤩
Rockstar🎓
Top SchoolJunwei Deng is a data-centric AI researcher and software engineer with eight years of experience building AI foundations and production ML systems across Intel and research labs. Currently a Ph.D. student in Information Sciences at UIUC and a Research Assistant, he blends deep academic training with industry practice—previously core-developing BigDL LLM tooling and improving performance and APIs at Intel and contributing documentation to the widely used intel/ipex-llm project. He has interned and collaborated with major tech teams at Microsoft and Google, and brings strong bench skills in benchmark design, API implementation, and customer-facing technical communication. Junwei’s background in electrical and computer engineering plus an MS in Data Science informs a pragmatic approach to model infrastructure, and his documentation-driven contributions show a rare focus on usability and developer experience in low-level LLM tooling.
8 years of coding experience
3 years of employment as a software developer
Master of Science in Information, Data Science, Master of Science in Information, Data Science at University of MichiganDoctor of Philosophy - PhD, Information Sciences, Doctor of Philosophy - PhD, Information Sciences at University of Illinois Urbana-ChampaignBachelor of Science - BS, Electrical and Computer Engineering, Bachelor of Science - BS, Electrical and Computer Engineering at Shanghai Jiao Tong University
Github Skills (8)
rs10
restructuredtext10
typos10
documentation10
transformers4
pytorch4
llm4
gpu4
Programming languages (5)
Github contributions (5)
intel/ipex-llm
May 2021 - Jan 2023
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:
Technical Writer
Technical WriterContributions:1095 reviews, 261 commits, 624 PRs in 1 year 8 months
Contributions summary:Junwei primarily focused on updating and refactoring documentation related to the "Chronos" component within the repository. Their commits involved revising user guides, fixing broken links, correcting typos, and restructuring the document organization. The contributions enhanced the clarity and usability of the documentation, including updates for API documentation and the addition of quick tour information. Overall, the user's work significantly improved the documentation quality and user experience.
deepspeedfine-tuninggemmagpuhuggingface
TheaperDeng/BigDL
Oct 2021 - Jul 2023
BigDL: Distributed Deep Learning Framework for Apache Spark
Contributions:494 pushes, 195 branches in 1 year 8 months
apache-sparkbigdldeep-learning
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.