George Stefanakis

George Stefanakis is a senior systems performance software engineer at NVIDIA, where he works on TensorRT-RTX to deliver adaptive, performant solutions for accelerated inference. Previously a researcher using ML for genomics at MIT's Uhler Lab, he brings experience across diverse deep learning frameworks and software stacks to his performance optimization work at NVIDIA. He holds bachelor's degrees in Computer Science and Mathematics and a master's degree in EECS, from MIT.
Avatar photo

Posts by George Stefanakis

Agentic AI / Generative AI

Adaptive Inference in NVIDIA TensorRT for RTX Enables Automatic Optimization

Deploying AI applications across diverse consumer hardware has traditionally forced a trade-off. You can optimize for specific GPU configurations and achieve... 9 MIN READ