Qi Yao
软件工程师 at 谷歌
Raleigh-Durham-Chapel Hill Area United States
Summary
🤩
Rockstar🎓
Top SchoolQi Yao is a software engineer with 11 years of experience blending systems, ML deployment, and low-level engineering, currently on Google's Cloud Hardware Simulation team in the Raleigh–Durham area. With a PhD in Mechanical Engineering and an MS in Computer Science from UW–Madison, Qi bridges rigorous research background and production-focused software development. Their open-source contributions to OpenMMLab (mmdeploy, mmcv, mmsegmentation) show deep expertise in ONNX/TensorRT integrations and model deployment tooling, while a C++ NES emulator project highlights practical systems-level coding and emulator accuracy improvements. Comfortable across hardware-aware simulation, ML inference optimization, and backend engineering, Qi brings a rare combination of academic depth and hands-on deployment experience.
11 years of coding experience
5 years of employment as a software developer
Master of Science - MS Computer Science, Master of Science - MS Computer Science at University of Wisconsin-MadisonMaster of Engineering - MEng Mechanical Engineering, Master of Engineering - MEng Mechanical Engineering at Northwestern Polytechnical University
Github Skills (22)
continuous-deployment10
pytorch10
c-language10
python10
tensorrt10
interrupt-handling10
onnx10
ml-deployment10
interrupt10
image-segmentation10
deep-learning10
segmentation10
sd-mmc10
cuda10
computer-vision10
Programming languages (6)
Github contributions (5)
open-mmlab/mmdeploy
Jun 2021 - Jan 2023
OpenMMLab Model Deployment Framework
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 863 reviews, 189 commits in 1 year 7 months
Contributions summary:Qi implemented and tested functionalities for model deployment using the OpenMMLab Model Deployment Framework (mmdeploy). Their contributions focused on integrating new features like registering rewriters for various functions to support different backends, adding TensorRT and ONNXRuntime support, and creating utilities for building and running tests. The user also worked on adding support for new object detection models.
pytorchncnnpplnndeep-learningdeployment
open-mmlab/mmcv
Sep 2020 - Dec 2022
OpenMMLab Computer Vision Foundation
Role in this project:ML Engineer
ML EngineerContributions:484 reviews, 55 commits, 58 PRs in 2 years 3 months
Contributions summary:Qi contributed to the implementation of custom operators within the mmcv library, focusing on supporting ONNX and TensorRT backends. Their work included adding ONNX support for ROI Align and ROI Pool, as well as integrating SoftNMS for ONNXRuntime. They also added TensorRT plugins for several operations, including Deformable Convolution, Grid Sampler, and others, indicating a focus on optimizing and extending the library for deployment scenarios.
visiondeep-learningcomputer-visionfoundationopenmmlab
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.