Description:

Design, build, and optimize scalable data ingestion and document processing solutions for unstructured insurance data.
Enable AI and retrieval systems using OCR, document intelligence, vector databases, and cloud-native data pipelines.

Requirements:

5-10 years of experience in Data Engineering, Data Processing, or Document Intelligence.
Strong programming skills in Python and SQL.
Hands-on experience with AWS services (S3, Step Functions, CloudWatch).
Experience with unstructured documents (PDF, Word, Excel, etc.) and OCR tools (AWS Textract or equivalent).
Familiarity with vector databases and RAG concepts.

Skills