Senior System Software Engineer, Agentic Inference - Dynamo

What you’d do

Develop open source software for serving AI model inference on GPUs, working on disaggregated serving for inference engines like vLLM, SGLang, and TRT-LLM. The role focuses on agentic inference workloads and distributed inference frontend development. Full time. Found on the employer's careers page on Sep 29, 2026. Apply through the link.