Build and operate on-premises infrastructure for containerized AI/ML services. Responsibilities include Kubernetes orchestration, infrastructure automation, CI/CD and GitOps pipelines, observability with Prometheus and Grafana, resilient high-availability infrastructure, and collaboration with mission stakeholders, data scientists, and system administrators. The role supports reliable delivery of mission-critical AI capabilities and may involve model-serving technologies, service meshes, SIGINT systems, and CNO operations.