AI Engineer
Build AI agents, RAG systems, evals and MCP servers that run in production.
- Location
- Groningen, hybrid
- Type
- Full-time
- Team
- Delivery
As an AI Engineer you design and build the AI systems our clients depend on: agents that take real actions, retrieval over messy document sets, and MCP servers that connect models to internal tools. You work on a project from the first conversation with the client through to the system running in production.
You care about whether a model does the job reliably, so you write evals before you tune prompts and you trace what happens once users arrive. You work closely with our full-stack and platform engineers, and you use coding agents in your own work with the same review standards as the rest of the team.
What you will do
- Design and build AI agents with tool use, approval steps and clear failure handling
- Build retrieval pipelines over documents, databases and internal systems
- Write and maintain eval suites that run on every release
- Build MCP servers that expose client systems to agents as secure, typed tools
- Choose models and hosting based on quality, cost and data requirements
- Monitor systems in production and improve them using traces and user feedback
- Explain trade-offs and results clearly to clients and colleagues
What you bring
- Several years building software in Python, with services running in production
- Hands-on experience building applications on top of large language models
- A practical understanding of retrieval, embeddings and vector search
- Experience testing non-deterministic systems, or a strong wish to do it properly
- Comfort working with APIs, databases and background jobs
- Clear written and spoken English
Nice to have
- Experience with LangGraph, PydanticAI or a similar agent framework
- Experience self-hosting open models
- Familiarity with Langfuse, Promptfoo or other LLM observability and eval tools
- Dutch, for conversations with some of our clients
What you will work with.
All technologiesHow hiring works.
- 01
Intro call
A short call to get to know each other, talk about what you are looking for and answer your questions. We reply to every application, whatever the outcome.
- 02
Practical conversation
We talk through real work: a system you built, a problem we recently solved or a small piece of code. No puzzles or whiteboard riddles.
- 03
Meet the team
You spend time with the people you would work with, see how we run projects and get a feel for the day to day.
- 04
Offer
If it is a good fit on both sides, we make a clear written offer and agree a start date that works for you.
Apply.
A link and a few sentences are enough to start. No cover letter needed.