Senior Python Data Engineer (OCR & Document Processing)- remote

Inetum; United States; Remote; USD 140,000 - 190,000; Full time

Job summary

Inetum is seeking a remote senior data engineer to build Python-based data systems that convert scanned and image documents into structured information. You will design, implement, and optimize OCR-driven pipelines that scale across varied document types and image qualities.

You will clean and structure OCR outputs, improve parsing accuracy, and ensure reliable delivery to downstream systems, all while mentoring teammates and upholding engineering standards in a distributed, remote US-based team.

Qualifications

• Senior-level experience with Python in production data engineering
• Hands-on familiarity with OCR libraries and document parsing techniques
• Strong understanding of ETL design, data modeling, and pipeline reliability
• Experience handling unstructured inputs such as PDFs, scans, or images
• Ability to work autonomously in a fully remote, distributed-team setting

Responsibilities

• Design and maintain Python data pipelines that ingest documents and run them through OCR workflows
• Build logic to clean, validate, and structure raw OCR output into reliable downstream records
• Improve parsing accuracy and throughput across varied document layouts and image qualities
• Integrate processed document data with analytical or operational systems that consume it
• Establish monitoring, error handling, and quality controls for document processing flows
• Contribute to engineering standards and mentor peers on data processing practices

Skills

Python

Data engineering

ETL design

Tools

OCR libraries

Document parsing

Job description

Role overview

A remote senior engineering role focused on building Python-based data systems that convert scanned and image-based documents into structured, usable information. The work combines data engineering with OCR and document processing pipelines, supporting operations that depend on accurate, large-scale extraction from unstructured inputs.

Responsibilities

• Design and maintain Python data pipelines that ingest documents and run them through OCR workflows
• Build logic to clean, validate, and structure raw OCR output into reliable downstream records
• Improve parsing accuracy and throughput across varied document layouts and image qualities
• Integrate processed document data with analytical or operational systems that consume it
• Establish monitoring, error handling, and quality controls for document processing flows
• Contribute to engineering standards and mentor peers on data processing practices

Requirements

• Several years of senior-level experience with Python in production data engineering work
• Hands-on familiarity with OCR libraries and document parsing techniques
• Solid understanding of ETL design, data modeling, and pipeline reliability
• Experience handling unstructured inputs such as PDFs, scanned files, or images
• Comfort operating independently in a remote setting with clear distributed-team communication