AI Data Enablement Engineer — Governed Data Products

Xenon Seven; Italia; On-site; EUR 70,000 - 110,000; Full time

Job summary

Xenon Seven is seeking a Data Enablement Engineer in Italy to design, build, and operate trusted data foundations for AI-enabled analytics. You will craft semantic models, governance, and data products that empower business users to interact with governed data via natural language interfaces.

You will work on Databricks-based data pipelines, Genie spaces, and RAG-enabled apps, collaborating with Finance stakeholders to translate domain needs into scalable data products.

Qualifications

• 5+ years hands-on data engineering on cloud data platforms with Databricks delivery.
• Hands-on experience with Databricks Genie in production pilots.
• Semantic layer / governed data products delivery with KPI definitions and business glossary alignment.
• Strong across dbt, PySpark, SQL, and Python.
• Orchestration with Airflow or Databricks Workflows.
• Data governance in regulated environments (RBAC, RLS, masking, lineage).
• Experience integrating structured and unstructured data into AI-enabled workflows.

Responsibilities

• Design and build AI-ready data products on Databricks with semantic models and KPI hierarchies.
• Implement semantic layers and governed datasets for BI and natural-language querying.
• Deploy and operate Databricks Genie spaces with Unity Catalog and tuning.
• Build RAG pipelines and interactive analytics apps (Streamlit/Databricks Apps).
• Engineer robust ETL/ELT pipelines (dbt, Airflow, PySpark).
• Implement data governance including RBAC, masking, lineage, auditing.

Skills

Databricks

Genie

Semantic layer

dbt

PySpark

SQL

Python

Airflow

Data governance

Structured data integration

Tools

Databricks

Airflow

dbt

Python

Job description

Xenon Seven is seeking a Data Enablement Engineer in Italy to design, build, and operate trusted data foundations for AI-enabled analytics. You will craft semantic models, governance, and data products that empower business users to interact with governed data via natural language interfaces.

You will work on Databricks-based data pipelines, Genie spaces, and RAG-enabled apps, collaborating with Finance stakeholders to translate domain needs into scalable data products.