Description
ElastixAI is hiring an Inference Infrastructure Software Engineer in Seattle on a hybrid schedule requiring three days per week in the office. The role owns the cloud and Kubernetes infrastructure for the company’s Token-as-a-Service platform, operating accelerated inference workloads across AWS, GCP, and on-premises environments. Responsibilities include cluster operations, software releases, AI accelerator scheduling, service reliability, cost optimization, automation, and collaboration with ML, runtime, and hardware teams. The position requires a bachelor’s degree in a relevant field, 3–5 years of Kubernetes experience, 2–3 years of production experience on AWS or GCP, and strong skills in Python, Bash, Go, Linux, infrastructure-as-code, and GitOps.
