Data Engineer + RAG + Micro Fabric
Responsibilities:
Design and implement data solutions for structured, unstructured, and vector data
Build and maintain ETL pipelines, data infrastructure, and validation frameworks
Support RAG implementations and enable LLM access to enterprise data
Provide data expertise to cross-functional and non-technical stakeholders
Skills Required:
3+ years in Data Engineering (ETL, data modeling, validation)Strong SQL, Python, and Apache Spark experienceETL tools: Kettle (Pentaho), Azure Data Factory, or similarDatabases: MS SQL, PostgreSQL, MySQL, MongoDB, Neo4JExperience with embeddings, RAG, and DataOps (Git, Docker, CI/CD)Exposure to Microsoft Fabric, Snowflake, Databricks, or DBT is a plus
