Data Engineer/Analyst

Role overview Build reliable ingestion and processing systems that convert large volumes of unstructured insurance documents into structured data for downstream retrieval and AI applications. The work spans document connectors, OCR and extraction, data preparation, and retrieval design, with attention to accuracy, security, and response-time commitments.

Responsibilities - Design scalable pipelines for documents including PDFs, scans, email, and Office files. - Connect ingestion workflows to enterprise sources such as SharePoint and email. - Integrate and tune OCR or document parsing tools to extract text and layout information accurately. - Automate cleaning, normalization, semantic chunking, and metadata tagging of extracted content. - Design vector storage schemas and retrieval mechanisms to supply data to RAG and other AI systems. - Add monitoring and validation loops to detect extraction errors or low-confidence OCR, and meet security and latency requirements. - Apply version control, CI/CD, and automated testing throughout the pipeline lifecycle.

Requirements - Five to ten years of data engineering experience. - Track record building document processing and ingestion pipelines on public cloud platforms. - Hands-on experience with unstructured documents such as PDFs, Office files, scans, and email. - Experience connecting to enterprise content sources, including SharePoint or email. - Practical experience with OCR or document extraction tools such as AWS Textract or an equivalent. - Proficiency with Python and SQL, plus Git, CI/CD, and automated testing. - Experience with AWS S3, Step Functions, and CloudWatch.

Nice to have - Experience with vector databases and RAG architectures, Azure, or Databricks. - Background in banking, insurance, or other financial services.

Benefits and work setup - Remote-first contract role for candidates based in Europe, with Central and Eastern Europe preferred. - The contract is expected to run through July 2027, with a possible extension.