Senior Document Processing Engineer

At Medius, we believe finance should be about strategy, not stress. Founded in Sweden in 2001, we’ve grown from a local startup into a global leader in cloud-based spend management. Thousands of organizations trust our AI-powered solutions to remove complexity, eliminate manual work, and give finance teams clarity, confidence, and control.

We’re more than a software company - we’re a global team of problem-solvers and innovators reinventing accounts payable. Our culture is built on freedom, curiosity, and continuous improvement, giving you space to focus on what matters and still have time to live your best life.

Join Medius and be part of a team where ideas matter, innovation thrives, and your impact is felt.

Learn more at www.medius.com

Job Overview

The Capture team at Medius builds the AI‑powered platform that automates invoice processing for customers worldwide. The Senior Document Processing Engineer will join a group of specialists developing the core subsystem that transforms raw PDFs and scanned images into structured invoice data. The role focuses on advancing a mature extraction engine that blends industry‑leading OCR, classical algorithms, and modern ML/LLM approaches. Success in this position means driving technical evolution, expanding support for new document types, and contributing to a scalable, cloud‑native architecture powering Medius’ global automation capabilities

 Responsibilities and Duties

• Develop and evolve the end‑to‑end automatic document processing pipeline—from OCR and text extraction to structured data output.

• Evaluate, test, and integrate new technologies and services as the extraction landscape evolves.

• Design solutions that bridge classical algorithmic methods with modern machine learning and LLM‑based techniques.

• Prototype new ideas in Python and build production‑grade services in C#/.NET on Azure.

• Work closely with ML specialists and engineering teams across Sweden, Poland, and Tunisia to deliver cohesive improvements to the extraction system.

Qualifications

• Experience in document processing, information extraction, OCR, NLP, or strong computer science fundamentals (algorithms, data structures, applied mathematics) with motivation to grow into the domain.

• Proficiency in automating, designing, building, updating, and maintaining appropriate test sets for effective benchmarking.

• Proficiency in C# and Python.

• Familiarity and comfort working across a cloud‑native environment using Azure and .NET technologies.

• Strong communication skills with fluency in English (team collaboration language).

Benefits

• Well-being perks: Multikafeteria program, private healthcare (LuxMed), life insurance

• Fun & connection: Summer & Xmas parties, Game Board nights, and spontaneous events