Anh-quan Cao
Research Scientist - Valeo.ai
Paris, Ile-de-France
Summary
👤
Senior🎓
Top SchoolAnh-quan Cao is a research scientist at Valeo.ai with 11 years of experience bridging academic depth and applied ML engineering in computer vision and deep learning. He earned a PhD-focused trajectory at PSL/École Polytechnique and has contributed to real-world projects across Valeo, Inria, Amazon, and TU Munich, including work on 3D uncertainty estimation, point cloud registration, and unsupervised CLIP fine-tuning with MLLM-generated text. His background spans startups and industry internships—founding two companies early in his career and delivering scalable algorithms such as distributed clustering using LSH during a CNRS internship. Comfortable moving between research and productization, he brings both theoretical rigor and hands-on experience deploying ML systems in automotive and perception contexts.
11 years of coding experience
4 years of employment as a software developer
Master of Science - MS, Data Science, Master of Science - MS, Data Science at Université Paris-SaclayBachelor of Science (B.Sc.), Computer Science, Bachelor of Science (B.Sc.), Computer Science at University of Science and Technology of HanoiHigher Diploma, Computer Software Engineering, Higher Diploma, Computer Software Engineering at APTECH Computer EducationMaster of Science - MS, Artificial Intelligence, Master of Science - MS, Artificial Intelligence at École PolytechniqueDoctor of Philosophy - PhD, Computer Vision, Deep Learning, Doctor of Philosophy - PhD, Computer Vision, Deep Learning at PSL Research University
English, French, Vietnamese
Github Skills (82)
github10
deep-learning10
3d10
depth-estimation10
scikit10
correspondence10
self-supervised-learning10
computer-vision10
3d-reconstruction10
git10
mayavi10
pytorch10
pytorch-lightning10
stream9
streaming9
Programming languages (9)
Github contributions (5)
astra-vision/SceneRF
Dec 2022 - Mar 2023
[ICCV 2023] Official implementation of "SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields"
Contributions:1 release, 28 commits, 1 PR in 3 months
3ddeep-learningnerfneural-radiance-fieldspytorch
astra-vision/MonoScene
Dec 2021 - Dec 2022
[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image
Contributions:3 releases, 2 reviews, 56 commits in 1 year
3dnyu-depth-v2semantic-scene-completionsemantic-scene-understandingsingle-image-reconstruction
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.