AI Platform Engineer

Job summary

The AI Platform Engineer builds and operates secure Generative AI infrastructure for software engineering teams in fully air-gapped, on-premise environments, hosted on high-performance GPU clusters. The role maintains containerized AI applications, RAG pipelines, local model serving and routing, multi-agent tooling, and internal observability, while implementing safeguards for prompt injection, data compartmentalization, and authorization. The platform uses technologies including Linux, Python, container orchestration, vector indexing, embeddings, and large language models.

Benefits

Qualifications

• Strong experience with Linux, containerization, and container orchestration in an on-premise data center.
• Strong Python programming skills.
• Experience building and integrating local APIs.
• Understanding of vector indexing, embeddings, and large language models.
• Excellent written and spoken English; Dutch is preferred.
• Must pass the national security screening (Verklaring van Geen Bezwaar).

Responsibilities

• Deploy, update, and maintain AI and developer tools on on-premise container orchestration platforms.
• Build and maintain air-gapped RAG infrastructure for retrieving context from internal codebases.
• Set up local model serving and develop flexible model-routing tooling.
• Support local multi-agent frameworks, memory systems, and tool integrations.
• Implement in-network monitoring and tracing dashboards for token usage, latency, and infrastructure costs.
• Implement security guardrails against prompt injection and enforce data compartmentalization and authorization.

Skills

Languages

Industry

Security clearance

Relocation