AI Engineer - GenAI & Customer Service

GeekSoft Consulting; Utrecht; On-site; EUR 70,000 - 110,000; Full time

Benefits offered by this job

Challenging environment

Learning opportunities

Job summary

GeekSoft Consulting is seeking an AI Data & Evaluation Engineer to join a Scrum team in Utrecht. You will prepare, structure, enrich, and validate enterprise data for AI knowledge bases and chatbots, and build Databricks pipelines for structured and unstructured data.

You will design evaluation datasets and apply testing and quality gates across data, prompts, models, and retrieval, with Azure, CI/CD, and IaC in a cloud-first environment.

Qualifications

• Work in a Scrum team to prepare, structure, enrich and validate enterprise data for AI knowledge bases and chatbots.
• Build and maintain Databricks data pipelines for structured and unstructured data for AI knowledge bases.
• Prepare, clean and enrich source data to improve AI information quality.
• Develop evaluation datasets covering realistic conversations, multi-step workflows and edge cases.
• Apply evaluation frameworks to test chatbots across single-turn, multi-turn and agentic scenarios.
• Implement automated testing, monitoring and quality gates for data, prompts, models, retrieval and orchestration.
• Deploy and manage cloud infrastructure using IaC, Azure Bicep and CI/CD pipelines.
• Analyze evaluation results and translate findings into improvements across knowledge, retrieval, prompts and tools.
• Strong proficiency in Python, data engineering and automated testing.
• Hands-on experience with Azure, Databricks, DevOps and CI/CD, preferably Bicep.
• Experience building data pipelines for AI knowledge bases and RAG applications.
• Experience with chatbot evaluation (multi-turn, simulated and agentic).
• Familiarity with Context Engineering, Agentic AI, Function Calling, retrieval strategies and tools.
• Strong engineering and data-quality mindset with Agile development.
• Strong ownership, accountability and problem-solving skills.
• Excellent communication and customer-focused approach.
• Relevant HBO or university degree and fluency in English.

Responsibilities

• Help design, build and continuously improve the clients online platform.
• Research, suggest and implement new technology solutions following best practices/standards.
• Take responsibility for the resiliency and availability of different products.
• Be a productive member of the team.

Skills

Python

Data engineering

Automated testing

Azure

Databricks

CI/CD

Infrastructure as Code

Bicep

Chatbot evaluation

English fluency

Agile development

Education

University degree in a relevant field

HBO preferred

Tools

Databricks

Azure DevOps

Bicep

Git

Job description

• Help design, build and continuously improve the clients online platform.
• Research, suggest and implement new technology solutions following best practices/standards.
• Take responsibility for the resiliency and availability of different products.
• Be a productive member of the team.

• Help design, build and continuously improve the clients online platform.
• Research, suggest and implement new technology solutions following best practices/standards.
• Take responsibility for the resiliency and availability of different products.
• Be a productive member of the team.

Requirements

• AI Data & Evaluation Engineer to work within a Scrum team, preparing, structuring, enriching, and validating enterprise data for AI knowledge bases and AI chatbots.
• Build and maintain Databricks data pipelines to process structured and unstructured data for AI knowledge bases.
• Prepare, clean, transform, and enrich source data to improve the quality and reliability of information used by AI assistants.
• Develop and maintain evaluation datasets covering realistic conversations, complex scenarios, edge cases, and multi-step workflows.
• Apply evaluation frameworks to test advanced chatbots across single-turn, multi-turn, simulation-based, and agentic scenarios.
• 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.
• Analyze evaluation results and translate findings into improvements across knowledge, retrieval, prompts, tools, and application logic.
• Strong proficiency in Python, 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 with chatbot evaluation, including multi-turn, simulated, and agentic interactions.
• Familiarity with Context Engineering, Agentic AI, Function Calling, retrieval strategies, and tool use.
• Strong engineering and data-quality mindset with an affinity for Agile development.
• Strong critical thinking, ownership, accountability, and problem-solving skills.
• Excellent communication skills and a customer-focused approach.
• Relevant HBO or university degree and fluency in English.

Benefits

• A challenging, innovating environment.
• Opportunities for learning where needed.