Linjie Luo
Research Manager at ByteDance
Palo Alto, California, United States
Summary
👤
Senior🎓
Top SchoolLinjie Luo is a Research Manager at ByteDance AI Lab who leads applied research in computer graphics and 3D computer vision, delivering technologies used across TikTok, Douyin and other global products. He has a strong track record of publishing more than 20 papers—18 in top-tier venues like SIGGRAPH, CVPR and ECCV—and holds over 10 granted US patents that have been productized into features like 3D stickers and marker tracking. Previously he was a Lead Research Scientist at Snap and a Research Scientist at Adobe, bringing deep AR and 3D scanning expertise to consumer-facing platforms. Linjie blends academic rigor (PhD from Princeton) with production engineering, evidenced by successful tech transfers and media-cited deployments. He also contributes to open-source ML projects (e.g., improving multi-object text recognition models with GPU optimizations), reflecting hands-on proficiency in model engineering and debugging. Based in Palo Alto, he excels at bridging novel research with scalable product impact.
8 years of coding experience
6 years of employment as a software developer
Bachelor of Science (BS), Computer Software, Bachelor of Science (BS), Computer Software at Tsinghua UniversityPhD, Computer Science, PhD, Computer Science at Princeton University
Chinese, English
Github Skills (6)
computer-vision10
pytorch10
mask-rcnn9
faster-rcnn9
cuda8
python8
Programming languages (2)
Github contributions (5)
Canjie-Luo/MORAN_v2
Jan 2019 - Dec 2022
MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition
Role in this project:
ML Engineer
ML EngineerContributions:75 commits, 7 PRs, 36 pushes in 3 years 11 months
Contributions summary:Linjie primarily focused on developing and modifying the `asrn_res.py` file, indicating a core involvement in the model architecture. Their commits involved the addition of CUDA options, suggesting efforts to optimize model training and inference on GPUs. They also updated `morn.py` which appears to be related to image pre-processing, and addressed some bugs, demonstrating debugging skills within the project.
pytorchtext-recognitionattention-mechanismdeep-learningrecognition
Canjie-Luo/Text-Image-Augmentation
Dec 2018 - Apr 2020
Geometric Augmentation for Text Image
Contributions:19 commits, 2 PRs, 18 pushes in 1 year 4 months
image-textpythonimage-processinggeometricaugmentation
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.