Xiaoli Liu
Software Engineer at Intel Corporation
Minhang District, Shanghai, China
Summary
👤
Senior🎓
Top SchoolXiaoli Liu is a software engineer with eight years of experience specializing in computer vision, image processing, and machine learning, currently based in Minhang District, Shanghai. At Intel she develops AI-driven app and game testing tools using C++, MCTS, neural networks and reinforcement learning, building on earlier work in pedestrian detection, stereo vision and camera calibration from her master's research. She has hands-on experience implementing and testing INT8 quantization and MKLDNN integrations in the PaddlePaddle deep learning framework, contributing to performance-critical operator kernels and unit tests. Xiaoli combines research acumen—evidenced by a camera-calibration patent and stereo vision projects—with production-grade engineering for automated driving, image recognition and detection systems.
8 years of coding experience
Master’s Degree, Computer Vision and Software Programming, Master’s Degree, Computer Vision and Software Programming at University of Shanghai for Science and Technology
English
Github Skills (10)
paddlepaddle10
machine-learning10
deeplearning-ai10
deep-learning10
python10
cprogramming-language9
neural-network9
c-language9
unit-testing9
distributed-training8
Programming languages (2)
Github contributions (5)
PaddlePaddle/Paddle
Dec 2018 - Mar 2019
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
Role in this project:
ML Engineer
ML EngineerContributions:24 commits, 24 PRs, 108 comments in 3 months
Contributions summary:Xiaoli's commits primarily focused on implementing and testing the `quantize` and `dequantize` operators, as well as integrating them with the MKLDNN backend. These changes included adding new operator kernels, modifying existing ones, and creating corresponding unit tests. The user also worked on enabling and testing the INT8 pool and conv operators, contributing to the overall efficiency and performance of the deep learning framework.
pytorchpythonparalleldeep-learningpaddlepaddle
xiaolil1/Paddle
Nov 2018 - Apr 2019
PArallel Distributed Deep LEarning
Contributions:94 pushes, 23 branches in 5 months
memory-efficientcaffe2paralleldeep-learningpaddlepaddle
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.