1155 | Senior Data Ingestion Engineer

Description: Design and implement scalable ingestion pipelines for high-volume structured and unstructured insurance documents (PDFs, scans, emails, Word, Excel, PowerPoint). Responsibilities include OCR/document extraction, text cleaning, semantic chunking, metadata tagging, vector storage/RAG preparation, validation, monitoring, and integration with downstream AI solutions. Requirements: At least 7 years of experience as a Data Engineer with Python and SQL. Minimum 5 years of experience with AWS, with practical examples. Proficient in Python, SQL, AWS, S3, Step Functions, CloudWatch, and data/document ingestion pipelines. Experience processing unstructured documents (PDFs, scanned documents, Word, Excel, PowerPoint, emails). Familiarity with OCR/document extraction technologies (AWS Textract or equivalent). Knowledge of connectors/integrations with sources like SharePoint and email. Skills in text cleaning, metadata extraction/tagging, automated error monitoring, and validation of OCR/extraction results. Experience with Git, CI/CD, and testing. Public-cloud data processing/document ingestion experience. English Level C1. Benefits: Opportunity to work on innovative data ingestion solutions in the insurance sector. One-year mission duration with potential for extension.