Description
NVIDIA is hiring a Senior DL Algorithms Engineer to implement language and multimodal model inference in NVIDIA Inference Microservices (NIMs), contribute to TRT-LLM, profile and optimize inference performance across the hardware and software stack, benchmark deep-learning models, and collaborate with software and hardware co-design teams. The role requires a PhD in computer science, electrical engineering, or computer science and engineering, or equivalent experience, along with 5+ years of experience, deep learning and neural-network expertise, GPU performance optimization skills, and proficiency in C++ and PyTorch or equivalent frameworks. The base salary range is 184,000 USD to 287,500 USD for Level 4 and 224,000 USD to 356,500 USD for Level 5, with equity and benefits; applications were accepted until February 22, 2026.
