Senior Data & Knowledge Engineer

Role overview Build data and knowledge systems that help people find reliable information across enterprise documents and datasets. The work spans retrieval-augmented generation (RAG), search, document processing, and knowledge graphs, with responsibility for data pipelines as well as secure, relevant retrieval in production. This is a remote role for candidates based in Costa Rica, Peru, Colombia, or Bolivia.

Responsibilities - Design RAG and enterprise search architectures, along with ingestion, transformation, enrichment, embedding, and indexing pipelines in Databricks. - Build and maintain Azure AI Search and vector search indexes with appropriate access controls, metadata, citations, lineage, and data freshness. - Create document extraction pipelines using Azure Document Intelligence for PDFs, forms, reports, engineering documents, and scanned materials. - Model entities, relationships, metadata, and domain context in knowledge graphs. - Measure and improve retrieval relevance and the quality of the knowledge available to users.

Requirements - At least five years in data engineering, search, analytics engineering, or knowledge platforms. - Practical experience with Azure Document Intelligence, Azure AI Search, Databricks, and SQL. - Experience delivering production data pipelines for ingestion, transformation, enrichment, embeddings, and indexing. - Strong grasp of vector search, embeddings, RAG, and enterprise information retrieval. - Experience designing or maintaining knowledge graphs with Neo4j or another graph database. - Understanding of metadata, data lineage, quality, governance, and knowledge management. - Ability to work with structured and unstructured data and secure retrieval patterns, including filtering, citations, access control, and freshness. - Bachelor’s degree in computer science, data engineering, data science, information systems, or a related field.

Nice to have - Advanced experience with Azure AI Search, Databricks, RAG, or vector search solutions. - Familiarity with document chunking, ranking, citation design, RDF, semantic modeling, or ontology design. - Azure Data Engineer or Databricks certification.

Benefits and work setup - Remote work from Costa Rica, Peru, Colombia, or Bolivia.