Data & Knowledge Engineer (Data Engineering, Data Science)

Project Description:

Provide governed data, enterprise knowledge, document intelligence, knowledge graph, and retrieval capabilities that ground AI agents in trusted evidence

Responsibilities:

• Design RAG and enterprise-search architectures.
• Build ingestion, transformation, enrichment, document extraction, embedding, and indexing pipelines in Databricks.
• Create and maintain Azure AI Search, vector search, and access-controlled retrieval indexes.
• Implement Azure Document Intelligence pipelines for extracting structured data from PDFs, forms, engineering documents, reports, and scanned content.
• Design and maintain knowledge graph models to represent entities, relationships, metadata, lineage, and domain context for agent reasoning and search enrichment.
• Implement metadata, filtering, citations, lineage, data freshness, and security-trimmed access controls.
• Measure and optimize retrieval relevance and knowledge quality.
• Support structured data products used by agents and deterministic services.

Mandatory Skills Description:

• Bachelor's degree in Computer Science, Data Engineering, Data Science, Information Systems, or a related field.
• 5+ years of data engineering, search engineering, analytics engineering, or knowledge-platform experience.
• Strong SQL skills and experience building production data pipelines in Databricks.
• Experience with data quality, metadata, lineage, and governance practices.
• Understanding of structured and unstructured enterprise information retrieval, including document extraction and knowledge graph patterns.

Nice-to-Have Skills Description:

• Hands-on Azure AI Search, Databricks, RAG, or vector-search experience.
• Experience with Azure Document Intelligence, document processing, chunking, embeddings, ranking, metadata, and citation design.
• Hands-on knowledge graph experience using Neo4j, RDF, graph databases, semantic modeling, ontology design, or entity-relationship mapping.
• Azure Data Engineer or Databricks certification.

Languages:

English: B2 Upper Intermediate