Business Intelligence & AI Context Engineer

Key Duties and Responsibilities:

Semantic and metric layer

• Define metric views, semantic models, KPI logic and business glossaries as the single certified definition of each measure.
• Create, improve and expand the scope of context and the Ontology for Genie.
• Prevent conflicting calculations across dashboards, Genie Spaces, reports and AI applications.

Decision products

• Build and optimize executive dashboards, operating dashboards and self-service analytical products.
• Create and manage automated, AI-ready dashboards that require no manual refresh or manual reconciliation.
• Design for the decision being made, not for the data that happens to be available.

Evaluation and trust

• Establish benchmark question sets, evaluation datasets, accuracy thresholds and usage monitoring for Genie Spaces and natural-language analytics.
• Test and publish answer accuracy, and remediate where accuracy falls below threshold.
• Monitor adoption and retire or rebuild products that are not used.

Business partnership

• Work with Data & AI Translators and business experts to encode definitions, exceptions, decision rules and narrative context.
• Support user enablement and self-service capability building.

Key Deliverables

• Certified KPI and metric definitions and the enterprise business glossary.
• Semantic models and the Genie ontology.
• Production dashboards and self-service analytical products.
• Evaluated Genie Spaces with published accuracy benchmarks.
• Adoption and usage metrics.

Accountability and Success Measures

• Metric consistency across every consumption channel.
• Accuracy of natural-language and AI-generated answers within the assigned scope.
• Analytical usability and decision relevance of delivered products.
• User adoption of dashboards and self-service tools.
• Currency of definitions as the business changes.

Working Relationships

• Internal: Data Engineers; Data & AI Translators; Data Scientists; AI / LLM Engineers; Data Governance Specialist; business owners; BI & Context Engineering Capability Head.
• External: platform vendor support.

Qualifications.

• Bachelor's degree in Computer Science, Information Systems, Statistics, Engineering, Business Analytics or a related field.
• Three or more years in business intelligence, semantic modelling or analytics engineering. Demonstrated ownership of enterprise metric definitions. Experience with natural-language analytics or LLM-based query interfaces is a strong advantage.
• Preferred: Power BI Data Analyst Associate, Databricks fundamentals. Optional: dbt or analytics engineering certification.

Technical Skills

• Advanced SQL; dimensional and semantic modelling.
• Power BI, including semantic models, DAX and performance optimization.
• Databricks, Unity Catalog metric views and Genie Spaces.
• Ontology and business-glossary design.
• Evaluation design for natural-language analytics — benchmark sets, accuracy measurement, regression testing.
• Visualization and dashboard design principles.
• Python for evaluation and automation is an advantage.