Yang Lu
Tech Lead Manager at TikTok
Seattle, Washington, United States
Summary
👤
Senior🎓
Top SchoolYang Lu is a Tech Lead Manager in Seattle with 9 years of experience building production ML systems at scale, currently leading e-commerce recommendation for videos, live streams, and products at TikTok. His background blends deep research (Ph.D. in Statistics from UCLA) with applied computer vision and machine learning work at Facebook and Amazon on video object detection, AR, and product classification. He’s an active practitioner of semantic segmentation and has contributed practical model implementations and training improvements (including focal loss integration) to an open-source TensorFlow/Keras repo covering many state-of-the-art architectures. Known for turning research insights into robust engineering, he navigates both academic rigor and product-driven deadlines. Colleagues rely on him to bridge model innovation with measurable business impact in high-throughput, real-world systems.
9 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Statistics, Doctor of Philosophy (Ph.D.), Statistics at University of California, Los Angeles
English, Chinese
Github Skills (9)
semantic-segmentation10
keras10
computer-vision10
deep-learning10
tensorflow10
python10
loss9
mask-rcnn9
faster-rcnn9
Programming languages (1)
Github contributions (5)
luyanger1799/Amazing-Semantic-Segmentation
Jul 2019 - Jul 2020
Amazing Semantic Segmentation on Tensorflow && Keras (include FCN, UNet, SegNet, PSPNet, PAN, RefineNet, DeepLabV3, DeepLabV3+, DenseASPP, BiSegNet)
Role in this project:
ML Engineer
ML EngineerContributions:74 commits, 3 PRs, 87 pushes in 1 year
Contributions summary:Yang primarily contributed to the implementation and modification of various semantic segmentation models within the repository. Their changes involved fixing typos, updating model architectures, and integrating new features such as focal loss. The user also modified the training and testing scripts, suggesting an active role in model development and evaluation. Their contributions span across several deep learning models, demonstrating a focus on computer vision tasks.
unetfcnpspnetsemantic-segmentationdeep-learning
luyanger1799/PSPNet-keras-master
Sep 2018 - Sep 2018
Contributions:12 commits, 11 pushes, 1 branch in 19 days
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.