Reza Zolfaghari
AI Lead And Co-Founder at Zebracat AI
Berlin, Germany
Summary
👤
Senior🎓
Top SchoolReza Zolfaghari is an AI lead and co-founder with 11 years of experience translating multimodal vision-language research into production-ready tools for video creation and marketing. He holds a PhD from the University of Freiburg under Prof. Thomas Brox, with publications at NeurIPS, ICCV and ECCV on video understanding, contrastive learning, and real-time efficient models. At Zebracat he leads generative multimodal pipelines and agentic LLM workflows to scale visual storytelling, having previously driven multimodal video research and open-source contributions at AWS. Reza combines deep academic rigor with hands-on product-building—leveraging large-scale social media video corpora to train practical models—making him fluent in both research and go-to-market execution. Based in Berlin, he’s particularly interested in how frames become stories and how vision and language can be bridged to democratize video.
11 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science | ML, Doctor of Philosophy - PhD Computer Science | ML at The University of FreiburgBachelor of Science 2005 2010 Computer Science, Bachelor of Science 2005 2010 Computer Science at Iran University of Science and TechnologyMaster of Science (M.Sc.) Artificial Intelligence, Master of Science (M.Sc.) Artificial Intelligence at Sharif University of Technology
German, Persian, tati, Turkish, English
Github Skills (69)
video-understanding10
action-recognition10
gluon9
image-text9
computer-vision8
object-detection8
contrastive-learning8
pose-estimation8
machine-learning8
time-management8
activity-recognition8
image-classification8
temporal8
semantic-segmentation8
mxnet7
Programming languages (6)
Github contributions (5)
mzolfaghari/chained-multistream-networks
Jan 2018 - Aug 2018
Code and models of paper " Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection" in ICCV 2017
Contributions:50 commits, 1 PR, 45 pushes in 6 months
classification
mzolfaghari/ECO-pytorch
Sep 2018 - Mar 2019
PyTorch implementation for "ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018
Contributions:18 commits, 1 PR, 17 pushes in 6 months
pytorchvideo-understanding
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.