AI Data Engineer

About the role

We are partnering with select clients to build enterprise‑grade, agentic AI solutions on Microsoft Fabric. You will design and deliver end‑to‑end AI pipelines that combine structured and unstructured data, enabling conversational experiences for teams across the Microsoft 365 ecosystem.

Key responsibilities

• Design and implement data pipelines, Lakehouse structures, Delta tables, and Direct Lake semantic models on Microsoft Fabric.
• Develop Retrieval‑Augmented Generation (RAG) patterns, including chunking, embedding pipelines, vector indices, and cosine‑similarity matching.
• Configure and fine‑tune Fabric Data Agents (or equivalent frameworks) with instruction prompts and example corpora.
• Train custom Azure AI Document Intelligence models on real documents and build semantic models for AI consumption.
• Deploy AI agents through Copilot Studio and publish them to Microsoft Teams.
• Collaborate with solution architects and client engineers, owning the technical build and guiding teams to maximise the solution’s value.

Required profile

• Proven ability to lead and own complex AI‑focused builds, working directly with client technical teams.
• Excellent communication skills to explain technical concepts to non‑technical stakeholders.
• Experience coaching junior engineers and providing pragmatic guidance on scope.

Required skills

• Microsoft Fabric (Lakehouse, Delta tables, Fabric Mirroring, Direct Lake, Data Engineering notebooks)
• RAG pipelines, chunking strategies, embedding pipelines, vector indices, cosine similarity matching
• Fabric Data Agents or equivalent agentic frameworks
• Azure AI Document Intelligence model training
• Semantic model creation (descriptions, synonyms, sample Q&A pairs)
• Copilot Studio deployment and Microsoft Teams integration

What we offer

• Both permanent and contract opportunities
• Exposure to cutting‑edge AI technologies within a collaborative, client‑focused environment