Senior Data Engineer

This is a fully remote position, open to applicants in Czechia.

📋 Description

• Design and develop scalable pipelines for processing large volumes of unstructured insurance documents.

• Create connectors for document sources like SharePoint and email.

• Integrate, configure, and optimize OCR and document parsing technologies to achieve high-accuracy text and layout extraction.

• Develop automated workflows for text cleaning, normalization, semantic chunking, and metadata tagging.

• Design vector storage schemas and effective retrieval mechanisms (RAG) to support downstream AI models.

• Ensure that document processing pipelines comply with enterprise security standards and low-latency SLA requirements.

• Construct automated error monitoring and extraction validation loops that identify low-confidence OCR outputs.

• Implement engineering best practices throughout the pipeline lifecycle, including version control, CI/CD, and testing.

• Transform significant volumes of insurance documents into structured, high-quality, AI-ready data for downstream RAG and AI models.

• Provide support to a Dutch insurance client through a consultancy focused on AI, automation, advanced analytics, and anti-financial crime.

⛳️ Requirements

• 5–10 years of experience in data engineering.

• Demonstrated experience in creating data processing and document ingestion pipelines on public cloud platforms.

• Practical experience in processing unstructured documents (PDF, Word, Excel, PowerPoint, scans, emails).

• Experience in building connectors to enterprise sources, such as SharePoint and email.

• Hands-on experience with document extraction/OCR tools, such as AWS Textract or similar.

• Strong engineering practices: Git, CI/CD, automated testing.

• Required: Proficiency in Python and SQL.

• Required AWS skills: S3, Step Functions, CloudWatch.

• Required OCR/document extraction experience: AWS Textract or equivalent.

• Required experience in unstructured document processing and ingestion pipelines.

• Required knowledge of Git, CI/CD, and testing.

• Experience in the banking or insurance sector is a plus.

• Nice to have: Familiarity with vector databases and RAG architectures.

• Nice to have: Experience with Azure and Databricks.

• Nice to have: Background in financial services/insurance domain.

• Must be based in Europe; candidates from CEE are preferred.

• Ability to commence work within 30 days.

🏝️ Benefits

• Long-term remote-first contract position.

• Contract duration through July 2027 with potential for extension.

• Remote work available within Europe (CEE preferred).