Senior Data Ingestion Engineer

• Design and implement scalable ingestion pipelines for high-volume structured and unstructured insurance documents
• Process PDFs, scans, emails, Word, Excel, and PowerPoint files
• Perform OCR/document extraction, text cleaning and normalization
• Apply semantic chunking and metadata tagging
• Prepare and store vector data for RAG
• Validate extraction results and monitor automated errors
• Integrate ingestion pipelines with downstream AI solutions and document sources

• At least 7 years of experience as Data Engineer with Python and SQL
• At least 5 years of experience with AWS
• Proficiency in Python, SQL, AWS, S3, Step Functions, and CloudWatch
• Experience building data/document ingestion pipelines
• Experience processing unstructured documents, including PDFs, scanned documents, Word, Excel, PowerPoint, and emails
• Experience with OCR/document extraction technologies, including AWS Textract or equivalent
• Experience building connectors/integrations with SharePoint and email sources
• Experience with text cleaning and normalization
• Experience with metadata extraction/tagging
• Experience with automated error monitoring
• Experience validating OCR/extraction results
• Experience with Git, CI/CD, and testing
• Public-cloud data processing/document ingestion experience
• Vector databases, RAG, semantic chunking, vector-storage schema design, and retrieval mechanisms are good to have
• Azure and Databricks are good to have
• AWS Textract specifically is good to have
• Experience within insurance/financial services is good to have
• Experience handling enterprise security and low-latency SLA requirements is good to have
• English Level C1
• Duration of the mission: 1 year