bardiadoosti
Summary
👤
SeniorBardia Doosti is a PhD-trained software engineer and researcher with eight years of experience applying deep learning to vision and audio problems, currently leading ML efforts for Google AR/VR. His work spans graph convolutional networks, 3D reconstruction, hand and body pose estimation, autoencoders and self-supervised architectures, with peer-reviewed contributions (including CVPR) from his time at Indiana University. He combines academic rigor with production-grade engineering at Google Cloud and AR/VR, and has interned on high-fidelity 3D reconstruction at Facebook Reality Labs. Comfortable across research and product environments, he brings a rare mix of pure mathematics, teaching experience, and large-scale codebase delivery to solve perceptual AI challenges.
8 years of coding experience
Github Skills (11)
graph10
pose-estimation9
python9
magenta9
music9
machine-learning9
deep-learning9
music-generation9
pytorch9
computer-vision9
generative-art8
Programming languages (1)
Github contributions (5)
bardiadoosti/HOPE
Sep 2019 - Oct 2020
Source code of CVPR 2020 paper, "HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation"
Contributions:13 commits, 17 pushes, 38 comments in 1 year
graphpose-estimationgraph-convolutiondeep-learningpytorch
bardiadoosti/GradCAM-PyCaffe
Oct 2017 - Jul 2019
Contributions:7 commits, 6 pushes, 1 branch in 1 year 8 months
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.