Solutions Architect, Inference Deployments

What you’d do

Build and optimize inference pipelines using tools like NVIDIA Dynamo, TensorRT-LLM, vLLM, and SGLang, and work with DevOps teams to orchestrate disaggregated inference on Kubernetes. Also mentor customers and internal teams through deployments and troubleshooting. Full time, based in Santa Clara, CA. Found on the employer's careers page on Sep 29, 2026. Apply through the link.