Data and AI Modeller / Analytics Engineer in Larne

• Description
• Data and AI Modeller / Analytics Engineer
• Make Power for Good

RES is the world's largest independent renewable energy company.

Our mission is simple: a future where everyone has access to affordable, zero-carbon energy.

The problems we're solving are among the most important of our generation — and the people working on them are extraordinary.

This is a rare opportunity to join a newly created global role within a growing central data and analytics team.

If you want to build the data foundation that the whole business depends on — at global scale, using cutting‑edge AI and data tooling — read on.

The Role

As Data and AI Modeller / Analytics Engineer, you'll own the design and build of RES's governed, reusable global data models — translating enterprise data into the business‑ready dimensions, facts, and metrics that power consistent reporting, self‑service analytics, and AI/ML at scale.

This is a hands‑on technical role that sits at the intersection of data engineering, business intelligence, and artificial intelligence.

You'll work across gold layer models, semantic models, and AI‑ready data products in Microsoft Azure Fabric — and you'll actively use LLMs, machine learning, and generative AI both as tools in your own workflow and as capabilities you enable for the rest of the business.

The quality of your models determines the quality of every AI output, every dashboard, and every business decision that flows from RES's data platform.

What You'll Do

• Semantic Modelling & Data Products
• Design and build governed gold layer models, semantic models, and certified data products — including dimensional models, canonical models, and reusable semantic structures across enterprise domains.
• Translate business rules, KPI definitions, and reporting logic into trusted, reusable metric logic; ensure consistency across dashboards, reports, and AI‑enabled tools.
• Design models that support self‑service analytics, natural language querying, and AI consumption — documenting metric definitions, calculation rules, filters, and caveats so outputs can be safely used by both people and AI tools.
• Own version control, testing, documentation, and governance of semantic models and metric definitions; identify and replace duplicate, conflicting, or ungoverned metrics with controlled enterprise definitions.
• AI & LLM Enablement
• Design and maintain semantic models purpose‑built for LLM and generative AI consumption — ensuring AI agents, copilots, and natural language querying tools access only certified, well‑governed definitions rather than raw or ambiguous data.
• Apply retrieval‑augmented generation (RAG) principles to data product design, enabling AI tools to retrieve accurate, contextualised metric definitions and business logic at query time.
• Validate AI‑generated analytical outputs against correct metric logic, approved filters, and certified semantic models — actively identifying and resolving AI answer risks including metric inconsistency, missing context, wrong filters, hallucinated definitions, and unsupported conclusions.
• Use LLMs and prompt engineering in your own workflow to accelerate model documentation, metric definition drafting, data lineage annotation, and consistency checking across large model libraries.
• Stay current with how LLM tooling and agentic AI frameworks consume structured data — and shape RES's semantic layer to be AI‑ready as these capabilities evolve.
• Machine Learning Enablement
• Produce feature‑ready datasets and ML‑optimised data products that data scientists and AI engineers can consume directly — reducing the data preparation burden and accelerating model development.
• Advise ML teams on data modelling requirements: feature engineering considerations, training/validation data structure, label availability, and the implications of business rule logic on model inputs.
• Design data products that support both batch ML pipelines and real‑time or near‑real‑time inference use cases.
• #J-18808-Ljbffr