Yawar Siddiqui is a Research Scientist at Meta Reality Labs with 11 years of experience bridging computer vision, graphics, and applied machine learning. He completed a PhD in Computer Vision at TUM and progressed from internships at Meta and Disney Research to a research scientist role focused on 3D generative models and performance capture. His background includes production-focused engineering at Adobe and hands-on contributions to markerless facial performance and neck-tracking algorithms, reflecting a rare mix of foundational research and shipped imaging software. Based in the Greater Munich area, he brings deep expertise in C++/Python systems and has repeatedly moved between academia and industry to translate novel vision research into practical pipelines. An understated strength is his comfort in both core imaging libraries and generative AI for 3D content, enabling work that spans low-level optimization to high-level model design.
11 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Vision, Doctor of Philosophy - PhD, Computer Vision at Technical University of Munich
Bachelor of Engineering (BEng), Computer Engineering, Bachelor of Engineering (BEng), Computer Engineering at Jamia Millia Islamia
Clean minimal implementation of Free-Form Image Inpainting with Gated Convolutions in pytorch lightning. Inspired from pytorch implementation by @avalonstrel.
Contributions:8 commits, 1 PR, 5 pushes in 1 year 3 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.