Senior System Software Engineer - Dynamo-Triton Inference Server

What you’d do

Develop GPU-accelerated AI inference serving software and work on merging the Triton Inference Server and NVIDIA Dynamo stacks into a unified platform for LLM and non-LLM workloads. Full time role in Santa Clara, CA, involving open source community work and optimizing prediction throughput and latency. Found on the employer's careers page on Sep 29, 2026. Apply through the link.