Igor Shovkun

Igor Shovkun is an engineer at NVIDIA who works on TensorRT-LLM, focusing on efficient inference for multimodal AI models. His work spans reasoning, video generation, GPU systems, and kernel optimization. Before joining NVIDIA, he was a high-performance computing engineer at SLB and a researcher at Stanford University. He earned a Ph.D. from the University of Texas at Austin and bachelor's and master's degrees in applied physics and mathematics from the Moscow Institute of Physics and Technology.