Use cases and hardware sizing
We match models to your use cases, number of users and latency targets, and size GPU servers for purchase, colocation or a private cloud.
AI on your own infrastructure
We run language models and AI assistants on servers in your data centre or private cloud, so documents, prompts and answers stay inside your network and under your control.
What we do
Scope of work
GPU servers and platform
Installation of GPU servers on bare metal, Proxmox VE, VMware or OpenShift, with Kubernetes and the NVIDIA GPU Operator, also in air-gapped networks.
Private language models
Open-weight models such as Llama, Mistral, Qwen or Gemma served with vLLM, Ollama or NVIDIA Triton behind an OpenAI-compatible API.
Search over internal documents
Retrieval-augmented generation on your file shares, SharePoint and databases, with a local vector store and the user's access rights respected in every answer.
Assistants and integrations
Chat assistants with single sign-on through Active Directory, Entra ID or Keycloak, and APIs that bring AI into your internal applications.
Security and operations
Network isolation, audit logs, GPU and response quality monitoring, and planned model updates, documented for GDPR, NIS2 and the EU AI Act.
Technologies
Typical technologies
We are not tied to any single vendor: we work on public and private clouds and adapt to your environment, licences and team skills. These are the tools we use most often in this area.
Compute and orchestration
- NVIDIA GPU Operator
- Kubernetes
- Proxmox VE
- VMware
- OpenShift
Model serving
- vLLM
- Ollama
- NVIDIA Triton
- llama.cpp
- LiteLLM
Models and platforms
- Llama
- Mistral AI
- Qwen
- Gemma
- Hugging Face
Vector search and retrieval
- pgvector
- Qdrant
- Milvus
- OpenSearch
Identity and secrets
- Keycloak
- Microsoft Entra ID
- HashiCorp Vault
Monitoring and observability
- Prometheus
- Grafana
- Langfuse
- OpenTelemetry
Related services
Often combined with this service
- OpenAI
- Claude
- Gemini
- Llama
AI & Automation Engineering
LLM-based assistants, document processing and process automation integrated with your systems.
- OpenAI
- Claude
- Gemini
- Llama
AI Services
From AI strategy and proof of concept to production: generative AI and machine learning solutions built into your products and processes.
Let's talk about your project
Tell us where you are today and what you want to achieve. We will suggest a concrete first step, and we can sign an NDA before any technical discussion.