Senior Data & Document Ingestion Engineer (OCR / RAG) – Remote

About the role

We are seeking a Senior Data & Document Ingestion Engineer to design and implement high‑volume pipelines that transform unstructured insurance content into retrieval‑ready data for AI and RAG systems. The role is fully remote, serving a Big 4 consultancy client working on AI‑driven transformation for financial institutions.

Key responsibilities

• Design and build scalable ingestion pipelines for PDFs, scans, emails, Word, Excel and PowerPoint files.
• Integrate OCR and document‑extraction tools (e.g., AWS Textract) to achieve high‑accuracy text and layout extraction.
• Develop workflows for text cleaning, normalization, semantic chunking and metadata tagging.
• Create connectors for enterprise sources such as SharePoint and email systems.
• Define data schemas and retrieval mechanisms for downstream AI and RAG use cases.
• Implement validation, monitoring and logging to detect low‑confidence extraction results and ensure security, reliability and latency requirements.

Required profile

• 5–10 years of professional data engineering or backend/data‑platform experience.
• Strong hands‑on experience with Python and SQL.
• Proven track record building data ingestion and document‑processing pipelines on public cloud platforms.
• Experience with OCR/document extraction tools such as AWS Textract.
• Fluent English and ability to work from anywhere in the EU.

Required skills

• Python
• SQL
• AWS Textract, S3, Step Functions, CloudWatch
• Git, CI/CD, automated testing
• SharePoint and email connector development
• Azure or Databricks (preferred)
• Vector databases, embeddings, RAG architectures (preferred)