Neo Zhang
Package Design Engineer at Broadcom
Sunnyvale, California, United States
Summary
🤩
Rockstar🎓
Top SchoolNeo Zhang is a seasoned package design engineer with 9+ years of experience leading packaging development for major semiconductor players including Arm, Broadcom, Amkor, and Samsung. He has driven first-of-kind chip packaging at Arm, led BGA and MTV designs, and developed automotive-grade power IC packages and reliability test programs. Based in Sunnyvale, he blends deep hands-on package architecture and cross-site design management with practical build and automation skills demonstrated by contributions to the ggml-org/llama.cpp SYCL backend for LLM inference. Neo's background in both semiconductor engineering (Master of Engineering from Fudan) and computer science underpins a rare mix of physical package expertise and software fluency, enabling efficient tooling, build automation, and device-specific optimization.
9 years of coding experience
14 years of employment as a software developer
工程硕士(Master of Engineering) Semiconductor Industory, 工程硕士(Master of Engineering) Semiconductor Industory at Fudan UniversityBachelor's degree Heating and Ventilation, Bachelor's degree Heating and Ventilation at University of Shanghai for Science and Technology
English
Github Skills (7)
sycl10
c-language10
gm10
cprogramming-language10
build-automation9
llm8
windows7
Programming languages (6)
Github contributions (5)
ggml-org/llama.cpp
Apr 2024 - Jul 2026
LLM inference in C/C++
Role in this project:
Back-end Developer & Automation Engineer
Back-end Developer & Automation EngineerContributions:36 reviews, 29 PRs, 9 pushes in 2 years 3 months
Contributions summary:Neo primarily contributed to the SYCL backend of the llama.cpp project, focusing on device-specific optimizations and bug fixes within the ggml-sycl.cpp file. Their work includes adding device information, removing unnecessary wait calls, and correcting API usages for SYCL operations. Additionally, the user made a change to the win-build-sycl.bat file, which indicates their involvement in building and packaging the project, particularly for Windows. This suggests an understanding of build processes and automation related to the SYCL implementation.
cppllm-inferenceggml
arthw/link
Apr 2018 - May 2023
Contributions:49 pushes in 5 years 1 month
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.