AI Platform Engineer

Job summary

The AI Platform Engineer builds and operates secure, on-premise AI infrastructure for engineering teams in fully air-gapped environments. The role includes deploying containerized AI tools on GPU clusters, maintaining local Retrieval-Augmented Generation (RAG) pipelines and model routing, supporting multi-agent systems, and implementing observability and security controls. The platform uses local large language models, vector indexing, embeddings, and Python-based integrations.

Benefits

Qualifications

• Experience with Linux, containerization, and container orchestration in an on-premise datacenter.
• Strong Python programming skills.
• Excellent written and spoken Dutch and English.
• Successfully pass national security screening (Verklaring van Geen Bezwaar).

Responsibilities

• Deploy, update, and maintain AI applications and developer tools on on-premise container orchestration platforms.
• Build and maintain on-premise RAG infrastructure and internal codebase retrieval pipelines.
• Configure local model-serving tools and flexible routing between local models.
• Support local multi-agent frameworks, memory systems, and tool interfaces.
• Implement locally hosted monitoring and tracing dashboards for token usage, latency, and infrastructure costs.
• Implement security controls to prevent prompt injection and enforce data compartmentalization and authorization.

Skills

Languages

Work schedule

Industry

Security clearance

Relocation