I will build rag pipelines, llm apps and generative ai agents
AI Engineer: RAG, Agents, n8n
Over deze dienst
Your team has documents, data and processes an LLM could put to work. Getting that into production reliably is the hard part, and it is what I do.
I build LLM-powered systems for real business use: RAG pipelines, AI agents that call your tools and APIs, and generative AI features inside your existing product.
WHAT I BUILD
- RAG pipelines: answers grounded in your documents, with sources cited
- AI agents: multi-step tasks, tool use, CRM and API integrations
- NLP: classification, extraction and summarisation of text and documents
- LLM integration: OpenAI, Claude and Gemini behind your own backend
STACK
Python, FastAPI, LangChain, LlamaIndex, OpenAI, Claude, Pinecone, Qdrant.
WHY ME
M.S. in Data Science. I build LLM systems full time as an AI engineer, with project experience in telecom, real estate, legal and recruitment. If an LLM is the wrong tool for your problem, I will say so before you order.
Message me with your use case and the data you have. I will reply with an honest view on whether it will work and how I would approach it.
Mijn portfolio
Veelgestelde vragen
Will the system make up answers?
It is built not to. Answers are drawn from your own documents, sources are cited, and when the documents do not cover a question the system says so instead of guessing.
Do I need my own OpenAI or Claude API key?
Usually yes, so usage is billed to you directly and you stay in control of cost. I will set it up with you in the first message. Open-source models are an option if your data must stay on your own server.

