Document Ingestion and Annotation Specialist
Developed and maintained pipelines for PDF document ingestion, extraction, and annotation using Mistral OCR and Typhoon OCR. Ingested and structured large volumes of unstructured PDF data into annotated and indexable formats via workflow automation. Labeled document content and metadata to support downstream AI/ML applications and searchable repositories. • Implemented automated ingestion and labeling for PDF documents. • Annotated metadata and document content using OCR-powered tools. • Worked with workflow automation and document processing platforms. • Enhanced the accuracy and usability of document annotation pipelines.