Ivy Li
Senior Technical Program Manager at Intel Corporation
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolIvy Li is a Senior Technical Program Manager with over a decade of experience driving complex platform and software programs across Intel, Quanta, and MiTAC, blending hardware validation, manufacturing NPI, and Linux-based product delivery. She has led lifecycle execution for 15+ Xeon server products and steered strategic validation platforms critical to processor success, while more recently managing AI-focused ecosystem adoption and video safety security software. Her background as a hardware engineer and hands-on work in signal integrity and functionality testing give her a rare systems-level perspective that spans silicon to software. Ivy is PMP- and Agile-certified, bilingual in Mandarin and English, and experienced leading cross-geo teams to resolve partner and factory issues. She also contributes to open-source ML tooling—optimizing DNNL integration in the widely used TVM compiler—showing she marries program leadership with practical engineering impact.
7 years of coding experience
20 years of employment as a software developer
Bachelor, Electronics and Information Engineering, Bachelor, Electronics and Information Engineering at Southwest University of Science and Technology
Github Skills (14)
compiler10
tvm10
machine-learning10
deeplearning-ai10
compiler-compiler10
deep-learning10
python9
cprogramming-language9
performance-optimization9
neural-network9
c-language9
convolutional-neural-networks9
tensor8
unit-test8
Programming languages (3)
Github contributions (5)
apache/tvm
Dec 2021 - Aug 2022
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
ML Engineer
ML EngineerContributions:13 reviews, 16 commits, 27 PRs in 8 months
Contributions summary:Ivy contributed to the optimization and extension of the DNNL (Deep Neural Network Library) integration within the TVM compiler. Their work included implementing support for new operations and fusion patterns, particularly focusing on Convolution and Dense layers, and post-ops like Swish and Clip. This involved modifying existing code and adding new test cases to ensure the integration's correctness and performance. The user also addressed bug fixes and layout optimizations.
metalvulkancompilertensoropencl
crazydemo/TLCBench
Sep 2021 - Sep 2023
Benchmark scripts for TVM
Contributions:1 release, 28 pushes, 3 branches in 2 years
benchmarkingtvmbenchmark-scriptsbenchmarkbitbake
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.