Senior AI Inference Platform Product Lead

NVIDIA in Santa Clara, CA, seeks a senior product leader to own the inference performance roadmap, shaping how models are represented, memory/state is managed, and tokens are generated. You will build scalable platforms across model families and deployment topologies for diverse customers.

You will define performance strategy for agentic workloads, coordinate with TensorRT-LLM, vLLM, SGLang, and NVIDIA Dynamo, and own benchmarking and release readiness while delivering credible performance