AI Data Platform Engineer - Governed Data & RAG

Xe7 Limited; España; Presencial; EUR 70.000 - 100.000; Jornada completa

Descripción de la vacante

Xe7 Limited is hiring a Data Enablement Engineer to design, build, and operate trusted datasets, semantic models, and embedded AI experiences that enable Finance users to interact with governed data in natural language.

You will craft AI-ready data products on Databricks, implement semantic layers, and deploy Genie spaces with Unity Catalog, while focusing on data governance and cost/performance optimization in a regulated pharma environment.

Formación

• 5+ years hands-on data engineering on cloud data platforms — Databricks demonstrated in real project delivery, not skill-list-only.

Responsabilidades

• Design and build AI-ready data products on Databricks — trusted datasets with well-defined business semantics, KPIs, hierarchies, and business glossary alignment.
• Implement semantic layers and governed datasets that support traditional BI and natural-language querying by business users.
• Deploy and operate Databricks Genie spaces with Unity Catalog, tuning them for accuracy, adoption, and business relevance.
• Build RAG pipelines and conversational analytics apps grounded in governed enterprise data.
• Engineer robust ETL/ELT pipelines (dbt, Airflow, PySpark) that produce and maintain trusted data for AI experiences.
• Implement data governance — RBAC, row/column-level security, masking, lineage, auditability, catalog and metadata management — in regulated pharma environment.
• Optimize cost and performance on data platform and AI sides (warehouse sizing, cluster tuning, token usage, caching, routing).
• Partner with Finance stakeholders to translate domain requirements into semantic models and governed data products they can trust.

Conocimientos

Databricks

Genie

Semantic models

ETL/ELT

dbt

PySpark

SQL

Python

Airflow

RBAC

Herramientas

Databricks Genie

Unity Catalog

Descripción del empleo

Xe7 Limited is hiring a Data Enablement Engineer to design, build, and operate trusted datasets, semantic models, and embedded AI experiences that enable Finance users to interact with governed data in natural language.

You will craft AI-ready data products on Databricks, implement semantic layers, and deploy Genie spaces with Unity Catalog, while focusing on data governance and cost/performance optimization in a regulated pharma environment.