Data and AI Engineer Amsterdam • KnappeKoppen

We are a Data & AI consulting firm that builds AI Agents and Interfaces for leading organisations across Europe. We help businesses go beyond simply using ChatGPT — our goal is to integrate AI into the core workflows, systems, and decisions that define how they operate.

Depending on the use case, this could mean building a retrieval-augmented knowledge system, designing agent workflows to automate internal tasks, or prototyping new AI-first products. The right AI solution depends on the business need — and we make sure it’s done right, end-to-end. We also work on integrating classic analytics solutions, from the right data infrastructure to Machine Learning models in production.

We also develop internal products, including:

• A secure, company-specific AI interface, allowing teams to interact with internal data, systems, and processes through natural language — with full control over privacy, infrastructure, and cost.
• A Marketing Intelligence Hub, an AI-/ML-driven decision platform that connects data, models, and insights to help marketing teams make faster, smarter decisions across channels and campaigns.

We’re looking for a pragmatic, ambitious Data and AI Engineer to help design, ship, and maintain data- and AI-powered tools and infrastructure. This is a hybrid role that combines hands-on client projects with internal product development.

You’ll be responsible for architecting and deploying full-stack data and AI applications, with a focus on solutions powered by Large Language Models (LLMs), Machine Learning models, Retrieval-Augmented Generation (RAG), and agentic systems.

A key part of your role will be to develop, evaluate, and monitor AI agents and ML-driven applications — ensuring that models behave as intended. Whether that means accurately referencing internal data, supporting creative workflows, or preventing hallucinations, you’ll make sure models perform reliably in real-world scenarios.

You’ll work across the entire stack: from data pipelines and vector databases to model integration and user-facing applications.

• Build and deploy AI systems powered by LLMs and internal/external data sources
• Design and maintain RAG pipelines using embeddings, vector databases, and knowledge stores
• Develop AI agents and tools that automate tasks, support users, or enhance creativity
• Evaluate model performance (e.g. hallucination rate, usefulness, latency)
• Extend and improve internal AI interface products for enterprise clients
• Work across open-source and hosted models (OpenAI, Claude, Mistral, Llama2/3, etc.)
• Integrate frameworks such as LangChain, Open WebUI, LiteLLM, N8N, and other orchestrators
• Deploy applications to cloud environments (mainly AWS with ECS, Lambda, and S3)
• Collaborate with both technical and non-technical stakeholders
• Build analytical tools and data infrastructure to make data reliably available for analysis

• 2+ years of experience in backend, data engineering, or ML roles, with at least 1–2 years working directly with LLMs or AI applications
• Hands-on experience with cloud deployment (AWS preferred), including containers or serverless services
• Experience setting up data pipelines (ETL/ELT)
• Strong Python development skills (FastAPI, LangChain, or similar frameworks)
• Experience building production-grade LLM pipelines (RAG, embeddings, vector stores like Qdrant or Weaviate)
• Familiarity with agentic AI tools (LangGraph, CrewAI, N8N, etc.) and workflow orchestration
• Understanding of LLM behaviour evaluation and guardrail implementation (or motivation to learn)
• Comfortable working independently and switching between client work and internal product development
• Startup-style mindset: resourceful, curious, iterative, and adaptable

• Basic frontend experience (React or Next.js)
• Familiarity with infrastructure-as-code (Terraform, Pulumi, AWS CDK)
• Experience integrating with third-party APIs, enterprise systems, or secure environments
• Prior work on internal tooling, chat interfaces, or workflow automation
• Contributions to open-source LLM/AI projects or a personal GitHub with experiments

• Work on both internal product development and high-impact client projects
• Help shape the technical foundation of next-generation AI tooling
• Collaborate directly with founders and engineers
• Flexible hybrid setup, with office presence in Amsterdam
• Fast-moving, high-learning environment with real responsibility and room to grow
• Salary indication: €4.000 - €6.000 per month