Senior Data Ingestion Engineer - Remote (EU) & OCR/RAG

Jimmy Technologies; United States; Remote; USD 101,000 - 141,000; Full time

Job summary

Jimmy Technologies is seeking a Senior Data / Ingestion Engineer for a long-term remote-first contract focused on ingestion pipelines for unstructured insurance documents. You will design scalable systems, integrate OCR, and build robust connectors to sources like SharePoint and email, enabling AI-ready data for RAG models.

The role prioritizes secure, low-latency processing for a European client base. The ideal candidate has 5–10 years in data engineering, strong Python/SQL skills, experience

Qualifications

• 5–10 years of data engineering experience.
• Hands-on with building data processing and document ingestion pipelines on public cloud.
• Experience processing unstructured documents (PDF, Word, Excel, PowerPoint, scans, emails).
• Experience building connectors to enterprise sources like SharePoint and email.

Responsibilities

• Design scalable pipelines for ingesting high-volume unstructured insurance documents.
• Build connectors to document sources such as SharePoint and email.
• Integrate OCR and document parsing to extract high-accuracy text and layouts.
• Create automated workflows for text cleaning, normalisation, semantic chunking, and metadata tagging.
• Design vector storage schemas and robust retrieval mechanisms (RAG) to feed downstream AI models.
• Ensure pipelines meet security and low-latency SLA requirements.
• Implement automated error monitoring and extraction validation for OCR outputs.
• Apply engineering best practices: version control, CI/CD, testing.

Skills

Python

SQL

OCR tools

CI/CD

Data pipelines

SharePoint

Git

Cloud platforms

Unstructured docs

Tools

SharePoint

Azure Databricks

S3

CloudWatch

Job description

Jimmy Technologies is seeking a Senior Data / Ingestion Engineer for a long-term remote-first contract focused on ingestion pipelines for unstructured insurance documents. You will design scalable systems, integrate OCR, and build robust connectors to sources like SharePoint and email, enabling AI-ready data for RAG models.

The role prioritizes secure, low-latency processing for a European client base. The ideal candidate has 5–10 years in data engineering, strong Python/SQL skills, experience