Jun Wang
Software Engineer III at Ericsson Canada
Nanjing City, Jiangsu, China
Summary
🤩
Rockstar🎓
Top SchoolJun Wang is a seasoned software engineer with over 6 years of experience and a long track record in telecom and systems software spanning Ericsson, Microsoft, Alcatel-Lucent Enterprise, and Huawei. Currently a Software Engineer III working on LTE eNB development and formerly promoted to Principal Engineer for architecture and innovation at Ericsson China, he blends deep protocol and network-stack expertise with hands-on implementation. Recently he has contributed as an ML engineer to Intel’s high-profile ipex-llm project, optimizing LLM inference and finetuning performance and improving first-token latency for real-world benchmarks. Based in Nanjing, he combines strong engineering rigor from carrier-grade systems with a growing focus on ML performance engineering. Known for pragmatic problem-solving, he moves between low-level optimizations and API-level integrations, making complex systems faster and more reliable. Ambitious about technical and product leadership, he continuously hones both technical depth and soft skills to scale impact.
6 years of coding experience
14 years of employment as a software developer
Master's Degree, Automation Engineer Technology/Technician, Master's Degree, Automation Engineer Technology/Technician at Southeast University
English
Github Skills (12)
llm10
transformers10
pytorch10
intel10
python10
gpu10
benchmark9
benchmarking9
quants9
quantization9
openvino8
onnx8
Programming languages (12)
Github contributions (5)
intel/ipex-llm
Nov 2022 - 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:
ML Engineer
ML EngineerContributions:10 reviews, 2 commits, 33 PRs in 1 month
Contributions summary:Jun primarily contributed to optimizing and enhancing the `ipex-llm` repository, focusing on accelerating LLM inference and finetuning. Their work involved developing and integrating APIs for model conversion, along with adding new functionalities. The user also addressed performance issues by implementing new methods for benchmarking and improving first token latency within the VLLM benchmark. Furthermore, they refined graphmode code, optimizing the overall system performance.
deepspeedfine-tuninggemmagpuhuggingface
ACupofAir/DataStructureWiki
Dec 2020 - Sep 2022
Contributions:51 commits, 48 pushes, 1 branch in 1 year 8 months
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.