Chunming Li
Director Of Software Engineering at 芯原
Chengdu, Sichuan, China
Summary
🤩
Rockstar🎓
Top SchoolChunming Li is a seasoned software engineering leader with 16 years of hands-on experience in low-level firmware, bootloaders, Linux, IP drivers, and system virtualization, now serving as Director of Software Engineering in Chengdu. He has led and scaled teams to deliver 10+ SoC projects, owning everything from boot ROM to board-level virtualization and customer-facing technical support. Currently he directs a 15-person team building a VeriSilicon QEMU-based virtual platform to accelerate software bring-up, combining IP modeling with SoC and board virtualization. His background includes device modeling and virtual platform work at Wind River and Intel, and practical exposure to performance debugging in high-performance ML frameworks like DeepRec. Known for instituting coding standards, training programs, and regular one-on-one coaching, he balances technical depth with people-first management. Colleagues value his ability to translate complex hardware/software co-verification challenges into pragmatic, production-ready tooling and processes.
6 years of coding experience
14 years of employment as a software developer
Bachelor's degree, Computer Science and Technology, Bachelor's degree, Computer Science and Technology at Chengdu University of Technology
English
Github Skills (12)
debugging10
debug10
machine-learning10
deep-learning10
tensorflow10
performance-optimization10
edn9
cprogramming-language9
bazel9
build-system9
c-language9
distributed-training8
Programming languages (2)
Github contributions (5)
DeepRec-AI/DeepRec
Mar 2021 - Jun 2022
DeepRec is a high-performance recommendation deep learning framework based on TensorFlow. It is hosted in incubation in LF AI & Data Foundation.
Role in this project:
ML Engineer
ML EngineerContributions:35 reviews, 21 commits, 22 PRs in 1 year 2 months
Contributions summary:Chunming's contributions primarily focus on optimizing and debugging machine learning operations within the DeepRec framework. They added Continuous Integration (CI) scripts for CPU builds, ensuring the framework's compatibility and performance on various hardware configurations. Moreover, the user addressed a segment fault issue in the Intel-optimized operations, demonstrating a deep understanding of low-level performance and debugging. They also incorporated enhancements from the oneDNN library for improved efficiency.
pythondeep-learningrecommendationdistributed-trainingmachine-learning
changqi1/xFasterTransformer
Oct 2023 - Jun 2024
Contributions:1 PR, 214 pushes, 54 branches in 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.