Description
NVIDIA is hiring a Senior System Software Engineer to develop GPU-accelerated AI inference serving software for the Dynamo-Triton Inference Server. The role focuses on feature development, customer adoption, convergence of the Triton and Dynamo stacks, production deployment, throughput and latency optimization, and contributions to open-source deep learning software. Candidates need a master's or PhD in computer science or a relevant field, at least five years of deep-learning software experience, strong Rust and C++ skills, and experience with high-scale distributed and machine learning systems. The base salary is 152,000–241,500 USD for Level 3 and 184,000–287,500 USD for Level 4, with equity and benefits, and applications were accepted until July 6, 2026.
