Engineering Manager, LLM Performance
NVIDIA
Santa Clara
Workplace: OnsiteFull timeUSD 224,000 - 431,250 annuallyFunction: Software EngineeringExperience: 7+ yearsEducation: mastersSkills: ["Leadership","Communication","Team-building","Architecture","Software-design","Production-quality","Collaboration"]Lead and grow a software engineering team focused on accelerating LLM/VLM/VLA inference across TensorRT LLM, vLLM, SGLang, and Dynamo on NVIDIA datacenter products. Architect and guide production-grade, high-performance inference software, collaborating with Researchers and GPU Architects to push optimization, scalability, and developer experience for next-generation AI across multiple architectures.
