Andrew Liu
Teaching Assistant at Paul G. Allen School of Computer Science & Engineering
Greater Seattle Area United States
Summary
🤩
Rockstar🎓
Top SchoolAndrew Liu is a software engineer and teaching assistant based in the Greater Seattle Area with nine years of experience at the intersection of machine learning, compilers, and systems. He has contributed to high-impact open-source projects like Apache TVM—implementing Relay features, TensorFlow frontend ops, and memory-saving automatic-differentiation passes—and has research experience in hardware-aware ML compiler optimizations. His internships at NVIDIA, Databricks, Jane Street, and Bloomberg reflect a blend of research-grade compiler work (including custom JAX/TensorFlow backends and multi-GPU pipelines) and practical distributed-systems engineering. At the University of Washington he supports courses in programming languages and operating systems while continuing research in ML accelerator co-design. He pairs a math and computer science background with hands-on contributions to production Android apps and large-scale data tooling, showing both depth in compilers and a pragmatic eye for user-facing quality.
9 years of coding experience
1 year of employment as a software developer
Bachelor's degree, Mathematics, Bachelor's degree, Mathematics at University of WashingtonETH Zürich
Github Skills (20)
tvm10
python10
machine-learning10
java10
android-developer10
javas10
relayer10
deeplearning-ai10
compiler-compiler10
deep-learning10
tensorflow10
android10
android-developers10
compiler10
qr-code10
Programming languages (11)
Github contributions (5)
apache/tvm
Mar 2020 - Jun 2021
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
ML Engineer
ML EngineerContributions:23 reviews, 14 commits, 19 PRs in 1 year 3 months
Contributions summary:Andrew primarily contributed to the Relay compiler, specifically in the context of TensorFlow frontend integration and automatic differentiation. Their work included adding support for new TensorFlow operations (Atan, Atan2) within the Relay framework. Furthermore, the user implemented a GradientCell Relay pass designed to optimize memory allocation during gradient computation, demonstrating a focus on deep learning compiler optimization. Additional work involved improving the type inference system and defunctionalization passes within Relay.
metalvulkancompilertensoropencl
getodk/collect
Jan 2020 - May 2020
ODK Collect is an Android app for filling out forms. It's been used to collect billions of data points in challenging environments around the world. Contribute and make the world a better place! ✨📋✨
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:2 PRs, 29 comments in 3 months
Contributions summary:Andrew primarily focused on enhancing the Android application's user interface and functionality. They removed a legacy settings feature from the QR Code configuration, refactored code, and added new UI components for the QR code scanner. The user also worked on integrating the QR code scanner into the app, including features like flash control and sound effects, while also improving the overall user experience.
challengingmhealthdata-collectionpointsmobile-data-collection
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.