Lead Enterprise AI Engineer
Doncaster - Remote
The Lead Enterprise AI Engineer is a hands-on technical role responsible for operationalising the organisation’s AI strategy. This individual will bridge the gap between business opportunities and technical implementation, taking use cases from concept to production.
The primary focus is to build and deploy intelligent agents and conversational interfaces using Microsoft Copilot tools and Databricks Mosaic AI. A critical component of this role is the curation of the "Semantic Layer”—to ensure AI models provide accurate, trusted answers to business questions.
Key Responsibilities
AI Solution Development & Agent Building
Design, build, and deploy low-code and pro-code AI agents using Microsoft Copilot tools to automate business workflows (e.g., HR queries, IT support, operational data retrieval).
Develop custom RAG (Retrieval-Augmented Generation) solutions within Databricks to allow LLMs to reason over proprietary SMS documents and data.
Integrate AI agents with enterprise systems (Dynamics 365, SharePoint, etc.) via APIs and Power Automate connectors.
Semantic Modelling & Databricks Genie Curation
Own the creation and maintenance of Databricks Genie Spaces. This involves translating complex database schemas into business-friendly semantic models.
Define and govern standard metrics, dimensions, and synonyms within Unity Catalog to ensure the AI "speaks the language of the business."
Continuously monitor Genie performance, reviewing "human feedback" on answers to refine the semantic model and improve accuracy over time.
Business Engagement & Prototyping
Partner with business stakeholders (Finance, Operations, Commercial) to decompose high-level use cases into technical requirements.
Rapidly prototype AI solutions to demonstrate value and gain quick traction within business units.
Act as a technical evangelist, demonstrating to non-technical teams how to interact with Genie spaces and Copilots effectively.
AI Operations (LLMOps) & Governance
Implement monitoring frameworks to track the cost, latency, and quality of AI model outputs.
Ensure all AI solutions adhere to the organisation's data governance and security standards (e.g., preventing data leakage via LLMs).
Manage the lifecycle of AI models and agents from development through to production and retirement.
Skills and Knowledge
Core Tech Stack: Deep hands-on experience with Azure/Microsoft Fabric ecosystem (specifically Copilot Studio & Power Platform) and Databricks (SQL, Unity Catalog, Mosaic AI).
Semantic Modelling: Strong ability to design data models for analytics. Experience with defining metrics layers (e.g., DBX semantic layer or Databricks Genie) is essential.
LLM & AI Engineering: Practical experience with Large Language Models (LLMs), Prompt Engineering, and RAG architectures.
Coding: Proficient in Python (for data manipulation and API interaction) and SQL (for data modelling).
Integration: Experience working with REST APIs and connecting disparate business systems.
Communication: Ability to explain technical AI concepts to non-technical business users and translate their feedback into code.