LLM/Data Engineer

Drive innovation with brainbay

full-time Utrecht, Netherlands (Hybrid Working)

Build the Future of AI in Real Estate

Are you a skilled LLM/Data Engineer passionate about creating scalable data solutions? At Brainbay, we’ve launched a groundbreaking AI assistant service tailored for NVM members. Join our AI Assistant team and contribute to shaping the future of AI in real estate through innovation, collaboration, and cutting-edge technology.

Your Role as a Data Engineer

As a LLM/Data Engineer, you’ll design, develop, and optimize data architectures, ensuring seamless and secure data access for AI applications and the AI assistant specifically. You’ll be developing and deploying large language model (LLM) applications in cloud environments. This critical role combines technical expertise, innovation and collaboration

About our Team

The team behind the NVM AI Assistant is one of brainbay’s newest teams. Together we are building a tool to help real estate professionals work smarter and deliver more value to their customers. Our team currently consists of three LLM Engineers, one Data Engineer, and two Full Stack Engineers with a mix of junior, medior, and senior experience. You’ll find plenty of opportunities to learn from experienced colleagues while also having the freedom to take ownership of your work and make a real impact. We believe that the best ideas come from people with different backgrounds, perspectives, and ways of thinking. And we encourage each other to contribute, ask questions, and help shape both our technology and our way of working. We support one another and enjoy celebrating our successes together. We value collaboration, curiosity, and continuous learning. Whether it’s exploring the latest developments in AI, discussing technical challenges over coffee, or organising a team outing, we make time to connect as people as well as colleagues. We want everyone to feel welcome, heard, and able to be at their best at work.

Key Responsibilities:

• Design and develop AI-driven solutions, focusing on practical, real-world applications;
• Design and manage scalable data architectures for LLM use cases;
• Build and maintain robust data pipelines from diverse sources to vector database in AWS;
• Implement role-based access control and data masking;
• Monitor and optimize processes with dashboards, logging, and incident management;
• Collaborate with cross-functional teams during Scrum events to ensure smooth execution;
• Test and optimize outcomes for precision and reliability.

What We’re Looking For

We’re seeking a self-motivated and curious data enthusiast who thrives in collaborative environments. You’re eager to learn and innovate while maintaining a sharp focus on delivering results.

Requirements:

You meet (at least some) of the following requirements:

• Proven experience in LLM application development and cloud deployment (AWS preferred);
• Knowledge of Retrieval-Augmented Generation (RAG) and prompt engineering;
• Experience preparing and curating datasets for LLM/RAG pipelines;
• Understanding of data versioning and lineage;
• Proficiency in Python, machine learning, RAG, AI agents (LangChain, LangGraph, MCP/UTCP), SQL/NoSQL databases, Git, and API development.
• Proficiency in structured and unstructured databases;
• Experience with vector databases, semantic search, and data orchestration tools;
• Knowledge of Agile/Scrum methodologies;
• Familiarity with CI/CD pipelines, ML Ops tools, and data pipelines;
• Fluent in English and Dutch.

Experience with the following areas can be beneficial, but are not essential:

• Familiarity with AWS services;
• Experience with Amazon Bedrock or similar LLM providers like OpenAI API;
• Background in real estate, preferably NVM Wonen.

What We Offer

At