Anthony Casagrande

Anthony Casagrande is a senior systems software engineer at NVIDIA and the technical lead for AIPerf, NVIDIA's benchmarking tool for generative AI inference. He specializes in measuring inference performance at scale, from single-GPU runs to multi-node Kubernetes deployments of NVIDIA Dynamo and other inference servers. His focus is on workloads that mirror production, and on measurements teams can trust and reproduce. Before joining NVIDIA, Anthony worked at Intel on Edge AI and RFID. He holds a B.S. in embedded computer systems from Arizona State University.