Ashwin Nanjappa is an engineering manager in the TensorRT team at NVIDIA. He leads the MLPerf Inference initiative to demonstrate the performance and energy efficiency of NVIDIA accelerators. He is also involved in improving the DL inference performance of the TensorRT library. Before joining NVIDIA, he worked on training DL models for CV, GPU-accelerated ML algorithms for depth cameras, and developing multimedia libraries for cellphones and DVD players. He has a Ph.D. in computer science from the National University of Singapore (NUS), with a focus on GPU algorithms for 3D computational geometry.