Senior Data Ingestion Engineer

The Data/Ingestion Engineer will design and implement scalable ingestion pipelines for high-volume structured and unstructured insurance documents, including OCR, text processing, and integration with downstream AI solutions. The role requires at least 7 years of experience as a Data Engineer with Python and SQL, and at least 5 years with AWS.

• Design and implement scalable ingestion pipelines for high-volume structured and unstructured insurance documents
• Perform OCR/document extraction
• Text cleaning and normalization
• Semantic chunking
• Metadata extraction/tagging
• Vector storage/RAG preparation
• Validation of OCR/extraction results
• Automated error monitoring
• Integration with downstream AI solutions

• At least 7 years of experience as Data Engineer with Python and SQL
• At least 5 years with AWS
• Python
• SQL
• AWS
• S3
• Step Functions
• CloudWatch
• Data/document ingestion pipelines
• Processing of unstructured documents: PDF, scanned documents, Word, Excel, PowerPoint, emails
• OCR / document extraction technologies
• AWS Textract or equivalent
• Connectors/integrations with sources such as SharePoint, email
• Text cleaning and normalization
• Metadata extraction/tagging
• Automated error monitoring
• Validation of OCR/extraction results
• Git
• CI/CD
• Testing
• Public-cloud data processing/document ingestion experience
• Vector databases (good to have)
• RAG (good to have)
• Semantic chunking (good to have)
• Vector-storage schema design (good to have)
• Retrieval mechanisms (good to have)
• Azure (good to have)
• Databricks (good to have)
• AWS Textract specifically (good to have)
• Experience within insurance / financial services (good to have)
• Experience handling enterprise security and low-latency SLA requirements (good to have)
• English Level C1 (good to have)