Engineering Manager, LLM Performance — Nvidia | cvGO!

Nvidia · US, CA, Santa Clara · Office

### About the Role Lead a team optimizing LLM inference and training performance on Nvidia GPUs. Define the performance roadmap for models like GPT, LLaMA, and Mistral. ### Responsibilities - Lead a team developing LLM optimization methods (quantization, pruning, KV-cache). - Define the performance