Senior Backend Engineer – AI Platform (Remote)

About the role

Claven AI is building a sovereign AI infrastructure that turns GPU clusters into cloud‑native AI clouds. We are looking for a senior backend engineer to own the core services that orchestrate AI/ML workloads on Kubernetes.

Key responsibilities

• Design, develop, and maintain Go services that route inference traffic, provision workloads, and manage their lifecycle on Kubernetes.
• Write custom controllers, operators, admission webhooks, and CRDs using controller‑runtime/kubebuilder, including GPU‑aware scheduling and placement.
• Integrate and optimise the model‑serving stack for cost, latency, and throughput, supporting multi‑GPU (tensor‑parallel) serving.
• Implement multi‑tenancy, network policies, quotas, and RBAC to support data‑sovereignty and air‑gapped modes.
• Define API contracts and collaborate with frontend engineers on gateway and identity layers.
• Diagnose and resolve production issues as pilot customers are onboarded.

Required profile

• Strong production‑grade experience with Go, building and operating real services.
• Deep knowledge of Kubernetes API, custom resources, and controller development.
• Hands‑on experience with GPU scheduling, model‑serving, and multi‑GPU workloads.
• Ability to take ownership, work autonomously, and learn quickly using AI‑assisted tools.

Required skills

• Go programming language
• Kubernetes (API, controllers, operators, CRDs)
• controller‑runtime / kubebuilder
• GPU‑aware scheduling and placement
• Model‑serving stack optimisation (cost, latency, throughput)
• Multi‑GPU (tensor‑parallel) serving
• Network policy, RBAC, quota management
• API design and integration