Senior Data & Document Ingestion Engineer (OCR / RAG)

About Gramian

Gramian Consultancy is a boutique consultancy specializing in IT professional services and engineering talent solutions. With a strong background in software engineering and leadership, we help companies build high-performing teams by matching them with professionals who truly fit their needs.

About the Role

Our client is a Big4 Consultancy group that works with leading financial institutions on AI-driven transformation, automation, advanced analytics, and financial crime prevention. Their work spans intelligent fraud detection, AML/KYC modernization, autonomous workflows, enterprise AI platforms, and the secure industrialization of AI in highly regulated environments.

We are looking for a Senior Data & Document Ingestion Engineer to build robust pipelines for processing high-volume unstructured insurance content. The role focuses on OCR, document parsing, ingestion pipelines, text normalization, semantic chunking, metadata extraction, and retrieval-ready data preparation for downstream AI systems.

CONTRACT: Contractor assignment, expected October 2026 – July 2027, with potential extension

COMMITMENT: Full-time

LOCATIONS: Europe-based, preferably CEE; remote, with potential future hybrid work in Prague

PROCESS: Initial qualification followed by technical and client interviews

NOTES: Fluent English is required. Strong AWS experience is highly preferred.

Responsibilities

• Design and build scalable document ingestion pipelines for PDFs, scans, emails, and office documents.
• Integrate and optimize OCR and document extraction technologies for high-accuracy text and layout extraction.
• Build workflows for text cleaning, normalization, semantic chunking, and metadata tagging.
• Process unstructured formats including PDF, Word, Excel, and PowerPoint.
• Develop connectors for enterprise sources such as SharePoint and email systems.
• Design data schemas and retrieval mechanisms for downstream AI and RAG use cases.
• Build validation and monitoring loops to detect low-confidence OCR or extraction results.
• Ensure ingestion pipelines meet enterprise security, reliability, and latency requirements.
• Implement logging, testing, and operational monitoring across data-processing workflows.
• Apply Git, CI/CD, and software-engineering best practices to pipeline development.

Requirements

• Approximately 5–10 years of professional data engineering or backend/data-platform experience.
• Strong hands-on experience with Python and SQL.
• Proven experience building data ingestion and document-processing pipelines.
• Hands-on experience processing unstructured documents such as PDF, Word, Excel, PPT, scans, or emails.
• Experience with OCR/document extraction tools such as AWS Textract or equivalent.
• Professional experience building data-processing pipelines on public cloud platforms.
• Experience with AWS services such as S3, Step Functions, and CloudWatch, or comparable cloud services.
• Strong development practices including Git, CI/CD, and automated testing.

Preferred Qualifications

• Experience with Azure, AWS, or Databricks in enterprise data environments.
• Experience with vector databases, embeddings, or RAG architectures.
• Experience designing connectors to SharePoint, email, or other enterprise content systems.
• Background in insurance, financial services, or regulated-data environments.