This internship is part of an AI-driven initiative focused on building data platforms that work with large-scale public and government datasets.

Interns will contribute to developing intelligent data ingestion pipelines that handle multiple formats such as PDFs, spreadsheets, and web-based content.

The role involves automating metadata extraction and organizing datasets through data classification techniques.

Interns will support the creation of vector-based data representations and help enable retrieval systems using RAG-style approaches.

Responsibilities include preparing both structured and unstructured data in a clean, usable format while maintaining proper data lineage.

The internship also offers exposure to hybrid data retrieval methods that combine SQL queries with vector-based search systems.

Interns will assist in building and supporting governance workflows, including schema creation, validation checks, and basic privacy or sensitive data detection.

This role is suitable for candidates interested in AI, data engineering, and building scalable data platforms for real-world use cases.