• Your responsibilities will include:Preparing, structuring, enriching and validating enterprise data for AI knowledge bases and conversational AI applications.
• Building and maintaining data pipelines in Azure Databricks for structured and unstructured data.
• Developing data and knowledge pipelines supporting RAG-based AI applications.
• Creating and maintaining evaluation datasets containing realistic conversations, complex cases, edge cases and multi-step workflows.
• Evaluating AI assistants across single-turn, multi-turn, simulated and agentic scenarios.
• Building automated testing, monitoring and quality gates covering changes to data, retrieval, prompts, models, orchestration and tools.
• Analysing evaluation results and translating them into improvements in retrieval, prompts, knowledge, tools and application logic.
• Deploying and managing Azure infrastructure using Infrastructure as Code, ideally Azure Bicep.
• Developing and maintaining CI/CD pipelines.
• Working with agentic AI concepts including context engineering, function calling, tool use and retrieval strategies.
• Contributing to production-ready, secure and reliable AI solutions within a regulated enterprise environment.

Your backgroundWe are looking for someone with a strong combination of AI engineering, data engineering and cloud engineering.

• You should have:Strong hands-on Python experience.
• Experience with data engineering and automated testing.
• Strong Azure experience.
• Hands-on experience with Databricks.
• Experience with Azure DevOps and CI/CD.
• Infrastructure-as-Code experience, ideally Azure Bicep.
• Experience preparing structured and unstructured data for AI knowledge bases.
• Strong experience with RAG / retrieval-based GenAI applications.