Engineering Manager Llm Performance Us Ca Santa Clara

NVIDIA is seeking an Engineering Manager to lead the development of next-generation LLM and VLM inference software technologies. This hands-on leadership role involves architecting solutions, optimizing performance across various frameworks like TensorRT LLM and vLLM, and guiding a team of engineers to deliver production-grade AI software. The position requires deep technical expertise in C++ or Python, strong management skills, and collaboration with researchers and GPU architects to set global standards for AI performance.