About QDNA
Aurélien works for a company that designs, sells, integrates and operates sovereign artificial intelligence platforms, on-premises or hybrid, from hardware through to production.
About this blog
Aurélien Ambert, CISSP.
Architect and pre-sales consultant for artificial intelligence and inference platforms.
He designs and operates local LLM inference platforms for production: deploying vLLM and NVIDIA NIM engines on GPU farms, tracking throughput in tokens per second and latency, then optimising. His background spans eighteen years in infrastructure, networking and security, with a specialisation in cloud-native security.
Certifications: CISSP (ISC2) and Microsoft Certified Azure Solutions Architect Expert.
Areas of expertise:
- open-weight models
- vLLM and NVIDIA NIM
- Kubernetes
- multi-agent orchestration
- data sovereignty
Our approach
Our method comes in five steps, from the need to day-to-day operation:
- Start from the need and the organisation's use cases.
- Choose the hardware suited to the organisation's profile.
- Serve interchangeable open models through a single gateway.
- Add multi-agent orchestration and memory.
- Operate the platform in compliance with GDPR, the objectives of the HDS certification and SecNumCloud.
The result is a platform operated in your own datacentres or in managed datacentres.
Case studies
QDNA designs, installs and operates platforms in production. A living example: gironde.qdna.fr.