Platform Engineer

AMroute LLC is seeking a highly skilled AI Infrastructure Engineer to design, build, and operate scalable GPU-enabled Kubernetes platforms for AI/ML workloads. The role involves managing Kubernetes clusters, building GPU infrastructure, and providing knowledge transfer to client teams.

Responsibilities:

• Design and manage Kubernetes clusters
• Build GPU-enabled infrastructure
• Deploy Longhorn storage
• Automate infrastructure using Terraform
• Monitor systems using Prometheus and Grafana
• Knowledge Transfer & Client Enablement
• Provide structured knowledge transfer (KT) sessions to client teams on all core platform components, including: Kubernetes architecture, operations, and troubleshooting, GPU infrastructure (NVIDIA stack, scheduling, resource optimization), Longhorn storage management and performance tuning, Canonical ecosystem tools (MAAS, Juju, Charmed Kubernetes)
• Develop and deliver technical documentation, runbooks, and training materials to support ongoing operations
• Conduct hands-on workshops and guided sessions to enable client teams to independently manage and scale the platform
• Act as a technical advisor, helping client stakeholders understand best practices in: Cloud-native infrastructure, AI/ML platform operations, Reliability, performance, and cost optimization
• Ensure smooth handoff of production systems with full operational readiness and support knowledge