Hui Huang
Senior Staff Engineer at Google DeepMind
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolHui Huang is a Senior Staff Engineer based in the San Francisco Bay Area with 11 years of experience optimizing large-scale ML inference and cloud resource efficiency. He has driven core inference performance for Google’s Gemini family and now focuses on accelerating Gemini inference on TPU at DeepMind, blending deep systems expertise with practical production impact. His background spans leading resource-efficiency teams for YouTube Ads and shaping GCP’s server and ML workload roadmap, reflecting a rare combination of product-scale engineering and hardware-aware architecture. A Ph.D. from UCLA, Hui brings research rigor to system design—early work includes accelerator virtualization and heterogeneous resource management from his startup days and measurable benchmark contributions to projects like PerfKitBenchmarker. Colleagues rely on him to squeeze latency and cost out of inference fleets while informing future hardware choices.
11 years of coding experience
15 years of employment as a software developer
B.S., Computer Science, B.S., Computer Science at Peking UniversityUniversity of California, Los Angeles
Chinese, English
Github Skills (11)
performance-tuning10
benchmarking10
benchmark10
performance-analytics10
performance-monitor10
performance-analysis10
performance-monitoring10
python10
performance-measurement10
gcp8
bash6
Programming languages (2)
Github contributions (4)
GoogleCloudPlatform/PerfKitBenchmarker
Mar 2015 - Apr 2015
PerfKit Benchmarker (PKB) contains a set of benchmarks to measure and compare cloud offerings. The benchmarks use default settings to reflect what most users will see. PerfKit Benchmarker is licensed under the Apache 2 license terms. Please make sure to read, understand and agree to the terms of the LICENSE and CONTRIBUTING files before proceeding.
Role in this project:
Backend Engineer
Backend EngineerContributions:6 commits, 4 PRs, 9 pushes in 1 day
Contributions summary:Hui primarily contributed to the `oldisim_benchmark.py` file, which indicates they focused on benchmark functionality. Their changes included integrating the oldisim framework, adding a cleanup phase to remove processes, and updating the file with Git versioning and flag prefixes. These modifications involved setting up and configuring the benchmark environment.
license-2licensedbenchmarkingapache-license-2pkb
GoogleCloudPlatform/oldisim
Feb 2015 - Apr 2015
Contributions:23 commits, 4 pushes, 1 tag in 1 month
benchmarkingworkloadsemulatebenchmarkbenchmarks
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.