AI Engineer (GenAI / LLM)

Reference: NL-TEST-AI-01 · Engagement: contract, 6 to 12 months, extendable · Start: within 4 weeks · On site: 2 to 3 days on site

IntelStack is hiring an AI Engineer for a global technology and consulting client delivering GenAI programmes for Dutch banks, insurers and public-sector organisations. You will take AI use cases from prototype to production, working in an English-speaking engineering team.

What you will do

• Build and deploy LLM-based applications: retrieval-augmented generation (RAG), agents and document processing.
• Design prompts, retrieval pipelines and evaluation sets, and measure accuracy, cost and latency.
• Integrate models (Azure OpenAI, Mistral, open-source LLMs) with enterprise systems through APIs.
• Put guardrails, monitoring and logging in place to meet EU AI Act and client risk requirements.
• Work with data engineers, architects and business owners to agree scope and success criteria.

Must have

• 5+ years in software or ML engineering, including 1+ year shipping GenAI or LLM solutions to production.
• Strong Python, plus REST APIs and microservices.
• Hands-on RAG experience: embeddings, vector databases (Azure AI Search, pgvector, Pinecone or similar), chunking and re-ranking.
• Cloud experience, ideally Azure (Azure OpenAI, AI Search, Functions, AKS).
• MLOps or CI/CD for model and prompt versioning.

Nice to have

• LangChain, LangGraph, Semantic Kernel or similar frameworks.
• Experience in financial services, insurance or government.
• Knowledge of responsible AI, model risk or AI governance.
• Dutch language.

Engagement details

• Working language English; Dutch is a plus.
• You must already have the right to work in the Netherlands (EU citizen or valid Dutch permit); no visa sponsorship.
• Freelance through your own company or employed through our payroll partner.