Bin Li
Engineering Manager at Beijing ShuZiJiaYuan Co,.Ltd.
Jiangsu, China
Summary
🤩
Rockstar🎓
Top SchoolBin Li is an engineering manager with 8+ years of professional experience and a strong foundation from Nanjing University (BS/MS in Computer Science). He has led engineering teams at Beijing ShuZiJiaYuan and Marvell Semiconductor and brings hands-on firmware and software experience from Xiaomi and Motorola. Technically fluent in ML inference and low-level optimization, he has contributed to the well-known MACE project—improving throughput tests, adding operators like ExtractImagePatches and Relu6, and optimizing convolution and GEMM kernels. Based in Jiangsu, China, he blends people leadership with deep systems expertise, often translating performance-sensitive research into production-ready mobile inference solutions. An understated strength is his long-term continuity across roles, reflecting both technical depth and stable team stewardship.
8 years of coding experience
10 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Nanjing University
Github Skills (9)
quantization10
machine-learning10
c-language10
deep-learning10
cprogramming-language10
performance-optimization10
tensorflow9
opencl8
mobile-development6
Programming languages (6)
Github contributions (5)
XiaoMi/mace
Apr 2018 - Apr 2021
MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.
Role in this project:
ML Engineer
ML EngineerContributions:266 commits, 7 PRs, 29 pushes in 3 years 1 month
Contributions summary:Bin's commits primarily focus on improving the functionality and performance of the `MACE` deep learning inference framework. They addressed a bug in the throughput test, enabling it to run correctly and integrated the `ExtractImagePatches` operator. Furthermore, the user has made optimizations for convolution and matrix multiplication kernels and also added support for new operations, such as Relu6, group normalization and dequantization.
neonpytorchheterogeneous-computingdeep-learning-inferenceheterogeneous
XiaoMi/nnlib
Mar 2019 - Mar 2020
Fork of https://source.codeaurora.org/quic/hexagon_nn/nnlib
Contributions:8 commits, 5 pushes, 25 comments in 11 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.