3 of 3 Contract Metadata Jobs in Central London

such as PyPDF2, pdfplumber, and AWS Textract Integration of OCR solutions (AWS Textract, Tesseract) for scanned documents Extraction of document structure (headings, tables, sections) Metadata extraction, normalization, and enrichment Handling of multiple document formats including PDF, HTML, and DOCX Data Integration Familiarity with SAP data structures is beneficial Integration with ...

Redshift, Lambda, and EventBridge. Build and optimise vector database solutions and embedding generation pipelines for semantic search. Implement document processing workflows (PDF parsing, OCR, metadata extraction). Integrate data from REST APIs , PIM systems, and potentially SAP. Ensure data quality, governance, and lineage tracking throughout the project. Required Skills ...

umbrella company for the duration of the contract. You must be able to implement and support content-related configurations and data pipelines, ensuring structured metadata and reliable delivery. You will have experience of designing and maintaining schemas, mappings and validation rules for content. You will also be able to build … teams on release readiness and automate checks and monitoring. Experience of Data Engineering and SQL, Python and ETL tools. You must have knowledge of metadata management and version control. Please apply ASAP to find out more. ...