Efficient DL Research Scientist: Quantization and Pruning

NVIDIA is seeking an Applied Deep Learning Research Scientist, Efficiency, to advance the efficiency of AI models and hardware. You will explore quantization, pruning, and novel numerics to optimize training and inference across Nemotron models and the broader platform. You’ll lead large-scale experiments, co-design future architectures and optimizers, and publish or open-source novel methods. Collaboration with cross-functional teams is essential to drive energy-efficient AI at scale. #J-18808-Ljbffr