Caroline Zhu
Software Engineer at Google
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolCaroline Zhu is a software engineer with nine years of experience building cloud-native and ML-enabled systems, currently working on Google Kubernetes Engine (GKE) at Google. Previously at Microsoft she contributed to the high-profile ONNX Runtime project, enabling on-device training in the browser and adding WebAssembly training APIs that power web-based ML workflows. She has hands-on backend and systems experience across production services, tooling, and automated UI testing, and has delivered proofs-of-concept for large language model training on-device. A Northeastern CS graduate who has taught large undergraduate classes and shipped code in both industry and freelance settings, she blends strong engineering rigor with a knack for making advanced ML capabilities accessible in client environments.
9 years of coding experience
3 years of employment as a software developer
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Northeastern University
Github Skills (15)
machine-learning10
c-language10
webassembly10
api10
cprogramming-language10
apidoc10
wasm-pack9
onnx9
rust-wasm9
deep-learning9
neural-network8
hardware-acceleration8
typescript-types7
typescript7
typescripts7
Programming languages (4)
Github contributions (5)
microsoft/onnxruntime
Jul 2022 - Mar 2025
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
Backend Developer
Backend DeveloperContributions:136 reviews, 83 PRs, 287 pushes in 2 years 8 months
Contributions summary:Caroline primarily contributed to the ONNX Runtime's WASM API, focusing on expanding its training capabilities. They implemented new API functions within `wasm/training_api` to support on-device training, including the addition of `OrtTrainingLoadCheckpoint`, `OrtTrainingCreateSession`, and related functions. This involved modifying existing files and creating new ones, specifically designed for integration with the WebAssembly environment. These changes aimed to enable ORT training web bindings, facilitating machine learning model training within web-based applications.
runtimetrainingtensorflowai-frameworkaccelerator
carzh/onnxruntime
Apr 2023 - Feb 2025
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Contributions:2 PRs, 330 pushes, 100 branches in 1 year 10 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.