remote
Data Engineer senior Azure - Contrat - Mia Innovation
Data Engineer
Senior Data Engineer (Azure) building a unified data foundation for an AI platform in legal services, consolidating disparate sources into a clean, neutral Common Data Model to feed RAG pipelines and conversational agents.
About the role
Key Responsibilities
- Design and implement a scalable Azure Data Lake architecture to ingest, store, and process heterogeneous legal, accounting, and document management data.
- Develop and maintain a Common Data Model (CDM) that ensures data consistency, neutrality, and compliance across the platform.
- Collaborate with the AI engineering team to integrate the CDM into Retrieval Augmented Generation (RAG) pipelines and conversational agents.
- Optimize data pipelines for performance, reliability, and cost-efficiency using Azure Data Factory, Databricks, and Synapse Analytics.
- Implement robust data governance, security, and compliance controls in line with legal industry standards.
Requirements
- 5+ years of experience in data engineering with a strong focus on Azure services.
- Proficiency in Azure Data Lake, Azure Data Factory, Azure Synapse, and Databricks.
- Solid background in data modeling, SQL, and Python for data transformation.
- Experience with RAG concepts and building conversational AI pipelines is a plus.
- Strong understanding of data governance, security, and compliance in regulated environments.