DevOps Engineer -AI Engineer for GenAI Assistants within Customer Service
DevOps Engineer -AI Engineer for GenAI Assistants within Customer Service
Role overview
You will prepare enterprise data and knowledge for advanced AI assistants and apply evaluation frameworks across single-turn, multi-turn, simulation-based, and agentic scenarios. You will work in a hybrid setup, collaborating closely with teams to implement conversational and AI concepts to ensure assistants provide accurate, grounded, and reliable support to advisors.
Key responsibilities
Collaborate within a scrum team to prepare, structure, enrich, and validate enterprise data for AI knowledge bases and chatbots.
Build and maintain data pipelines in Databricks to process structured and unstructured data for AI knowledge bases.
Apply evaluation frameworks to test chatbots across single-turn, multi-turn, simulation-based, and agentic scenarios.
Prepare, clean, transform, and enrich source data to improve information quality and reliability for AI assistants.
Create and maintain evaluation datasets covering realistic conversations, complex cases, edge cases, and multi-step workflows.
Implement automated testing, monitoring, and quality gates for changes to data, prompts, models, retrieval, and orchestration.
Deploy and manage cloud infrastructure using Infrastructure as Code (particularly Azure Bicep) and CI/CD pipelines.
Analyse evaluation results and translate findings into improvements across knowledge, retrieval, prompts, tools, and application logic.
Your profile
Mindset: Strong engineering and data-quality mindset with an affinity for Agile development; proactive, hands-on approach; strong critical thinking, ownership and accountability.
Communication: Excellent communication skills and customer-centric attitude.
Education & Languages: Relevant HBO or university degree. Fluency in English and Dutch mandatory.
Required skills
Strong proficiency in Python and experience with data engineering and automated testing.
Hands-on experience with Azure, Databricks, DevOps, CI/CD, and Infrastructure as Code (preferably Bicep).
Experience building data pipelines and preparing structured and unstructured enterprise data for AI knowledge bases and RAG applications.
Experience applying evaluation methods to advanced chatbots, including multi-turn, simulated, and agentic interactions.
Familiarity with Context Engineering, Agentic AI, Function Calling, retrieval strategies, and tool use.
Work model: Hybrid; ideally one day per week onsite in Utrecht. The team coordinates remote/office days and works from the office on Mondays.
Contract type: Freelance/self-employed (ZZP) not allowed.