Senior System Software Engineer, Agentic Inference - Dynamo

Build GPU-accelerated inference infrastructure for Dynamo, developing open-source components that serve trained AI models and support agentic workloads. You’ll advance disaggregated serving across vLLM, SGLang, and TensorRT-LLM, improve inference-state management with KV/prefix cache reuse via NIXL, and evolve a distributed inference frontend with stateful, multi-turn semantics. Partner with team leads to prioritize features, load-balance async requests, and optimize throughput under latency constraints.