Nutanix NCP-AI case studies
Nutanix NCP-AI · Put your knowledge to work in context.
The Nutanix Certified Professional - AI (NCP-AI) is a professional-level certification for infrastructure engineers, platform architects, and virtualization specialists who design, deploy, and operate AI workloads on Nutanix infrastructure. It validates that you can reason about the full stack rather than a single product: the AI architecture and its components, GPU virtualization and workload placement, AI-ready deployment patterns such as GPT-in-a-Box, the data services layer (storage, Objects, and databases), Kubernetes-based containerized AI workloads through the Nutanix Kubernetes Platform, day-two operations and lifecycle management, and the security, governance, and multitenancy controls that surround shared GPU capacity. The Nutanix NCP-AI case studies are 5 cases and about 3,852 words.
1Consolidating a Hospital AI Platform Before Pilot Expansion
Northvale Health System runs a private AI platform for radiology and clinical documentation. The environment has two Nutanix clusters: a 3-node management cluster running Prism Central and NKP management components, and a 6-node workload cluster with 24 NVIDIA L40S GPUs.
812 words, about 4 min2GPU Sharing for a Regulated Quant Research Group
Meridian Capital's quant research group has 22 data scientists and a production risk engine. The AI platform runs on AHV across two Nutanix nodes, each with four NVIDIA A100 80GB GPUs, for eight GPUs total.
797 words, about 4 min3Deploying a 70B RAG Assistant on GPT-in-a-Box
Outdoor retailer Trailhead is deploying a 70B-parameter open-weight assistant on Nutanix GPT-in-a-Box and Nutanix Enterprise AI. The validated design has three H100 80GB nodes, eight GPUs total, NKP, Nutanix Objects for model artifacts and documents, and a PostgreSQL-based vector store.
745 words, about 4 min4Fixing GPU Scheduling and Autoscaling on NKP
Brightline Media runs 28 containerized inference services for captioning, moderation, and recommendation on Nutanix Kubernetes Platform. The cluster has three control-plane nodes and six workers; two workers have four L40S GPUs each.
743 words, about 4 min5Tenant Isolation in a Shared AI Assistant Platform
CloudLens is a SaaS provider offering a shared AI assistant to three healthcare customers on one Nutanix Kubernetes Platform cluster. Each tenant has a namespace, a Nutanix Enterprise AI inference endpoint, and an Objects bucket for documents.
755 words, about 4 min