Applied Scientist II · Amazon

Muhammad Usama Saleem

Scholar· GitHub· LinkedIn· X· Email

I'm an Applied Scientist II at Amazon, where I develop large-scale multimodal AI systems for real-world operational and customer experiences. I received my Ph.D. in Computer Science from the University of North Carolina at Charlotte in 2026, advised by Prof. Pu Wang in the GENIUS Lab. I was previously a Research Scientist Intern at Google's Extended Reality (AR/VR) team, and my work includes a U.S. Patent on 3D human pose and movement estimation from monocular images.

My research builds multimodal foundation models that unify real-time perception with high-fidelity synthesis: 3D human pose estimation and mesh reconstruction via generative masked modeling, and multimodal motion synthesis frameworks for controllable, high-quality 3D human animation in real time. Ultimately, I aim to create AI systems that both understand human behavior in the physical world and synthesize interactive digital counterparts within immersive XR environments.

Open to research collaborations and opportunities — reach me at usama.saleem7977@gmail.com.