AI-Driven Backend Developer: Document Conversion

TransPerfect; Madrid; Híbrido; EUR 45.000 - 70.000; Jornada completa

Descripción de la vacante

TransPerfect is hiring a Backend Developer to join its AI team, focusing on converting complex PDFs to editable .docx while preserving visual structure. You will compare ABBYY, Adobe, AWS Textract with open-source AI tools and build a Python-based pipeline that combines OCR engines with docx generation.

You will work across a global team, researching and refining layouts, fonts, and nested tables to ensure pixel-perfect results.

Formación

• Proficient in Python with strong OpenCV/PyMuPDF experience.
• Hands-on OCR/Document AI with Tesseract, PaddleOCR, or transformer models.
• Familiarity with XML-based formats (OOXML) and document structure.

Responsabilidades

• Lead research and implement the document conversion pipeline.
• Evaluate commercial vs open-source OCR and AI-native solutions.
• Develop Python-based workflow integrating OCR engines with document generation tools.
• Experiment with layout correction using LLMs and layout-aware models.
• Tackle edge cases like rotated text, low-res scans, complex notation.

Conocimientos

Python

OCR/Document AI

XML/OOXML

LLM Integration

Architectural vision

Herramientas

OpenCV

PyMuPDF

python-docx

Tesseract

PaddleOCR

LayoutLMv3

Donut

Nougat

Descripción del empleo

TransPerfect is hiring a Backend Developer to join its AI team, focusing on converting complex PDFs to editable .docx while preserving visual structure. You will compare ABBYY, Adobe, AWS Textract with open-source AI tools and build a Python-based pipeline that combines OCR engines with docx generation.

You will work across a global team, researching and refining layouts, fonts, and nested tables to ensure pixel-perfect results.