Products / SVC-02
Managed services · SVC-02

AI Platform Deployment — up to 4 nodes

Kubernetes, NVIDIA GPU Operator, inference stack, model registry, queues and monitoring, production-ready in two weeks.

16.900 €excl. VAT

Estimated delivery: 10 days. Confirmed on order acceptance.

Warranty and support includedTPV Virtual Banco Santander · Bank transfer

Overview

We turn up to four GPU nodes into an operable platform: Kubernetes orchestration, GPU Operator, inference server (vLLM or Triton), model registry, training-queue management, monitoring with SPEM Observe, operations documentation and handover to the customer's team.

Included

  • 12-month SPEM Observe licence for the deployed nodes
  • 4-hour handover session

Specifications

Duration2 semanas
ScopeHasta 4 nodos GPU
DeliverablesPlataforma operativa, runbooks, sesión de traspaso