Yiyun Miao
Software Engineer at Baidu
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYiyun Miao is a software engineer with 11 years of experience building and optimizing large-scale recommendation, ranking, and inference systems across Baidu, YY Inc., and Meta (Faceb00k). She has deep domain expertise in CTR prediction, preranking/ranking pipelines, transfer and pre-training workflows, and production inference for recommendation engines. At PaddlePaddle/Paddle-Lite she contributed XPU backend kernels and performance-focused op fusion work, showing a hands-on ability to push ML models to edge and specialized hardware. Her background combines research-grade skills from Tsinghua with practical leadership as a tech lead manager, frequently bridging algorithm development and systems engineering. Colleagues rely on her to translate complex model improvements into stable, high-throughput production services.
11 years of coding experience
11 years of employment as a software developer
Master of Science (MS), Computer Software Engineering, Master of Science (MS), Computer Software Engineering at Tsinghua UniversityBachelor of Science (BS), Computer Software Engineering, Bachelor of Science (BS), Computer Software Engineering at Beijing Institute of Technology
英语 english, 中文 chinese
Github Skills (7)
paddlepaddle10
embedded10
c-language10
deep-learning10
cprogramming-language10
back-end-development10
xpu10
Programming languages (4)
Github contributions (5)
PaddlePaddle/Paddle-Lite
Apr 2020 - Apr 2021
PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）
Role in this project:
Back-end Developer
Back-end DeveloperContributions:4 reviews, 9 commits, 17 PRs in 11 months
Contributions summary:Yiyun primarily contributed to the XPU backend for PaddlePaddle Lite. Their commits involved adding and enhancing XPU op kernels, including the implementation of features like precision switching within existing operations. They focused on fusing operations for performance improvements, specifically related to multi-encoder structures and embedding operations. Furthermore, the user addressed bug fixes and improved the existing XPU infrastructure.
inference-enginemobilebaidutensorflowfpga
Cwndmiao/bce-fpga-dev-kit
Mar 2017 - Oct 2017
Contributions:114 commits, 3 PRs, 162 pushes in 7 months
dev-kitbcedevfpga
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.