Yu-han Liu
Software Engineer at Google
United States
Summary
🤩
Rockstar🎓
Top SchoolYu-han Liu is a software engineer with 11 years of experience specializing in ML, MLOps, and backend systems, currently building robotics-related infrastructure at Google. With a PhD in mathematics, he blends rigorous academic problem-solving with hands-on engineering—helping migrate and harden cloud ML workloads, implement health/readiness checks and autoscaling, and improve SDKs and testing for Vertex AI and Google Cloud client libraries. He has a track record of productionizing models on GCP (App Engine, Cloud Storage, TPUs) and contributing to widely used repos like googleapis and googlecloudplatform, where his work spans API versioning, sample migrations to GAPIC, and test automation. Colleagues rely on him to make ML deployments reliable and maintainable; less obvious is his cross-language fluency from Python to Ruby and experience writing both technical docs and unit tests that keep large ecosystems healthy.
11 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy (PhD), Mathematics, Doctor of Philosophy (PhD), Mathematics at The Ohio State University
Chinese, English
Github Skills (47)
google-cloud-platform10
python10
apidoc10
api-design10
gcloud10
api-client10
testing10
rspec10
storage10
machine-learning10
google-app-engine10
tpu10
reinforcement-learning10
gcp10
ruby10
Programming languages (13)
Github contributions (5)
GoogleCloudPlatform/ml-on-gcp
Sep 2017 - Nov 2019
Machine Learning on Google Cloud Platform
Role in this project:
MLOps Engineer
MLOps EngineerContributions:125 commits, 40 PRs, 69 pushes in 2 years 2 months
Contributions summary:Yu-han's primary contributions focused on deploying and managing a machine learning model on Google Cloud Platform. They implemented health checks and readiness checks for the deployed model, ensuring it was loaded before accepting traffic. The user also added health check and autoscaling to the model, and added a client. The commits centered on creating a production-ready environment for a machine learning model using Google App Engine and Google Cloud Storage.
gcpgoogle-cloud-platformmachine-learningcloud-platformgoogle-cloud
googleapis/python-aiplatform
Sep 2020 - Jan 2023
A Python SDK for Vertex AI, a fully managed, end-to-end platform for data science and machine learning.
Role in this project:Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:299 reviews, 79 commits, 199 PRs in 2 years 3 months
Contributions summary:Yu-han's primary contribution involves regenerating the v1beta1 code, indicating work focused on API versioning and potentially code generation. They also addressed bug fixes related to the prediction service and unit tests, improving the reliability of model deployment. The user set up sample testing configurations, indicating a focus on improving the testing infrastructure. Additionally, they exported the aiplatform_v1beta1 as aiplatform.gapic_v1beta1, likely in preparation for SDK refactoring.
pythonend-to-endsciencedata-sciencemachine-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.