Remote job
Senior Data Engineer
Job details
About this role
Role overview
A senior data engineering assignment with a consultancy that helps banks and insurers modernize through AI, automation, and analytics, with particular depth in Anti-Financial Crime and enterprise AI platforms. The engineer will join a delivery for a Dutch insurance client, building ingestion pipelines that turn high volumes of unstructured insurance documents into AI-ready data feeding RAG systems and downstream models. It is a long-term remote-first contract position for candidates based in Europe.
Responsibilities
- Design and implement scalable pipelines for ingesting high-volume unstructured insurance documents including PDFs, scans, emails, and Office files - Build connectors to enterprise document sources such as SharePoint and email systems - Integrate, configure, and optimize OCR and document parsing technologies for high-accuracy text and layout extraction - Build automated workflows for text cleaning, normalization, semantic chunking, and metadata tagging - Design vector storage schemas and retrieval mechanisms to feed downstream AI models - Implement error monitoring and confidence validation loops on OCR outputs - Apply engineering best practices including version control, CI/CD, and automated testing across the pipeline lifecycle
Requirements
- 5-10 years of experience in data engineering - Proven track record building data processing and document ingestion pipelines on public cloud platforms - Hands-on experience processing unstructured documents across common formats - Experience building connectors to enterprise sources such as SharePoint and email - Practical experience with OCR or document extraction tools, for example AWS Textract or equivalent - Strong engineering practices including version control, CI/CD, and automated testing
Nice to have
- Experience with vector databases and RAG architectures - Familiarity with Azure or Databricks - Domain experience in financial services or insurance
Benefits and work setup
- Remote-first within Europe, with Central and Eastern Europe preferred - Long-term contract running until July 2027, with possible extension - Start date: ASAP - Contract under EU legislation