Python Backend Developer

TransPerfect; Lisboa; Presencial; EUR 45 000 - 65 000; Tempo integral

Resumo da oferta

TransPerfect is seeking a creative and passionate Backend Developer to join our innovative AI team in Lisbon, Portugal. This full-time, permanent position focuses on solving complex document processing challenges, converting unstructured PDFs into editable .docx files.

The ideal candidate will lead the research on AI-native OCR solutions and implement a robust document conversion pipeline using expert Python skills. Explore cutting-edge models to optimize document fidelity and structural recognition.

Qualificações

• Expert-level Python skills with experience in OpenCV, PyMuPDF, and python-docx.
• Deep familiarity with Tesseract, PaddleOCR, and modern Transformer-based document models.
• Understanding of XML-based document formats (OOXML) and precise visual fidelity.

Responsabilidades

• Lead the research and implementation of document conversion pipeline.
• Perform comparative analysis of AI-native OCR solutions.
• Establish metrics for format fidelity.

Conhecimentos

Python skills

OpenCV

PyMuPDF

python-docx

Tesseract

PaddleOCR

Vision-Language Models

XML-based document formats

GPT or Claude models

Descrição da oferta de emprego

About us

TransPerfect, a recognized leader in translation software with a vibrant start‑up spirit, is seeking a creative and passionate Backend Developer to join our innovative Artificial Intelligence (AI) team. The AI team has become a core driver of the company's innovation in machine translation, generative AI, natural language processing, and automation.

About the Role

As a Backend Developer, you will help us solve the "last mile" of document processing: converting complex, unstructured PDFs into perfectly formatted, editable .docx files; the goal is not just to extract text, but to recreate the visual and structural intent of the original document—including nested tables, multi‑column layouts, font hierarchies, and styling.

You will lead the research and implementation of our document conversion pipeline. This hybrid role requires both strategic decision‑making and hands‑on development, combining engineering and AI skills.

• Perform comparative analysis of commercial and open‑source AI‑native OCR solutions.
• Establish metrics for format fidelity to objectively measure how well a tool recreates headers, footers, tables, and styles.
• Build a Python‑based workflow that integrates OCR engines with document generation libraries.
• Explore and fine‑tune Vision‑Language Models or LayoutLM‑style architectures to improve structural recognition.
• Optimize edge cases such as rotated text, low‑resolution scans, and complex mathematical notation.

Job Requirements

• Expert‑level Python skills with experience in OpenCV, PyMuPDF, and python‑docx.
• Deep familiarity with Tesseract, PaddleOCR, and modern Transformer‑based document models (LayoutLMv3, Donut, or Nougat).
• Understanding of XML‑based document formats (OOXML) and precise visual fidelity.
• Experience using GPT or Claude models for layout correction and semantic cleanup.
• Ability to decide when to use an off‑the‑shelf API versus building a custom pipeline.

Nice to Have

• Experience with Pandoc AST for format conversion.
• Background in DTP, Typography or Graphic Design.
• Contributions to open‑source OCR or PDF manipulation projects.

Location & Employment

Lisbon, Portugal — Full‑time, Permanent