Margaret Qian
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolMargaret Qian is an engineering manager in San Francisco with 10 years of experience building scalable AI and ML infrastructure. She currently leads a Databricks team developing an optimized, production-grade AI model serving engine. Her background spans MosaicML, OctoML and Facebook, combining research and production systems expertise. An active open-source contributor to Apache TVM, she has implemented Relay and QNN passes, improved bfloat16 support and added ONNX shape-slicing capabilities — work that bridges low-level compiler and quantization internals with real-world deployment needs. She holds a BS in Computer Science from Columbia (3.84 GPA) and has a track record of turning complex ML compiler ideas into production-ready systems.
10 years of coding experience
9 years of employment as a software developer
Bachelor's Degree, Computer Science, 3.84, Bachelor's Degree, Computer Science, 3.84 at Columbia University in the City of New York
Chinese
Github Skills (14)
compiler10
tvm10
machine-learning10
compiler-compiler10
deep-learning10
python10
deep-learning-ai10
relaymodern10
relay10
compilers10
onnx9
bfd8
tensorflow7
tensorflow27
Programming languages (2)
Github contributions (5)
apache/tvm
Feb 2022 - May 2022
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
ML Engineer
ML EngineerContributions:14 reviews, 8 commits, 8 PRs in 3 months
Contributions summary:Margaret primarily contributed to the development of the TVM compiler stack, focusing on the "Relay" intermediate representation and its QNN (quantized neural network) capabilities. Their commits involved implementing and testing new passes for extracting and transforming fake quantized operations, specifically in the context of operators like adaptive average pooling, leaky ReLU, and mean. They also worked on improvements to existing QNN-related code, including fixing issues related to bfloat16 support, adding ONNX shape slicing capabilities, and making code formatting improvements.
metalvulkancompilertensoropencl
margaretqian/tvm
Jan 2022 - Jun 2022
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Contributions:28 pushes, 13 branches in 4 months
cpugpu-programminggpu-accelerationtvmdeep-learning
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.