Overview
The role contributes to the digitization of archival records by ensuring proper metadata management and indexation for all digitized archival records. It also involves processing digital-born records to make them machine-readable and managing the resulting data for proper indexation.
Tasks Summary
- Oversees from a business perspective the optical character and layout recognition (OCR and HTR) pipeline.
- Implements quality control protocols to verify the quality of the OCR process output.
- Cleans and complements both descriptive and technical metadata and ensures proper indexation in the archival management system.
- Contributes to the maintenance and evolution of the ICRC archives metadata frameworks.
- Contributes to the development of the knowledge graph and the semantic search capabilities.
- Supports the ongoing process optimization by providing feedback and suggestions for improvement.
- Provides advice and solutions on building a highly automated sustainable digital archiving pipeline.
- Is knowledgeable and pro-active in the field of AI to harness the power of LLMs.
Experience Requirements
- Professional experience as archivist, librarian or data scientist
- Expertise in descriptive, administrative and technical metadata standards (e.g. RiC, Dublin Core, MODS, PREMIS, METS, ISAD-G)
- Experience with AI-driven data modelling, semantic search and linked data principles (RDF, SPARQL)
Qualification Requirements
• University Degree in Archives, Information Science or related field , or equivalent professional experience