Summary
Pooya Fayyaz is a Video Foundation Model Researcher with eight years of experience at the intersection of computer vision, robotics, and self-supervised deep learning. He has led research and engineering efforts from academia to industry, including building advanced video diffusion and character-consistent generation pipelines at Sorenson and now developing Hollywood-grade virtual production tools at Voia. His PhD work and research collaborations (including with Amazon) span human and object pose estimation, navigation, and novel self-supervised methods that improve robustness and inference efficiency. Known for turning core research into real-time systems, he has a track record of optimizing models for production constraints while preserving generation quality. Based in Washington, DC, he combines deep academic rigor with a practical curiosity—summed up simply on GitHub as “I'm just curious”—that drives continual experimentation and cross-domain innovation.
8 years of coding experience
9 years of employment as a software developer
Bachelor's degree Computer Engineering, Bachelor's degree Computer Engineering at Iran University of Science and Technology
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at George Mason University