Description
NVIDIA is hiring an Engineering Manager to lead and grow an engineering team focused on accelerating LLM, VLM, and VLA inference software across TensorRT LLM, vLLM, SGLang, and Dynamo. The role combines hands-on technical leadership with software architecture, performance optimization, benchmark tuning, production-quality library development, project planning, and cross-functional coordination. Candidates need advanced technical education, at least seven years of software engineering experience including three years of technical leadership, and expertise in C++ or Python, LLM/VLM inference, and preferably GPU architecture and CUDA. The posting is marked hybrid and offers a base salary of 224,000–356,500 USD for Level 3 and 272,000–431,250 USD for Level 4, plus equity and benefits.
