Chang Liu

Chang Liu is a senior software engineer at NVIDIA, specializing in AI inference and high-performance computing. He leads diffusion-based image and video generation efforts in TensorRT LLM, focusing on software architecture, scalability, and performance optimization. His experience spans large language models, multimodal systems, graph neural networks, and distributed computing. Previously, he developed and optimized sparse matrix solvers at Cadence Design Systems. Chang holds a Ph.D. in computational electromagnetics from the University of Texas at Austin.