About the job
About us:
TransPerfect, a leading name in translation technology, is on the lookout for a dynamic and innovative Backend Developer to join our cutting-edge Artificial Intelligence (AI) team. As part of this division, you will have the chance to influence the future of AI within a global framework. Over the past decade, our AI team has evolved into a pivotal force driving innovations in machine translation, generative AI, natural language processing, and automation.
We seek an experienced backend developer who is passionate about pushing technological boundaries and making a significant impact in the AI sector. You will collaborate with a diverse, international team of experts from the USA, Spain, Portugal, and India. If you are enthusiastic about developing robust and scalable solutions that enhance AI accessibility, this role is perfect for you.
About the Role:
As a Backend Developer, you will tackle the critical challenge of transforming complex, unstructured PDFs into well-formatted, editable .docx files. Your mission will be to not only extract text but to faithfully recreate the visual and structural elements of the original documents, including nested tables, multi-column layouts, font hierarchies, and styling.
Your responsibilities will include leading the research and implementation of our document conversion pipeline. This hybrid role requires both strategic decision-making regarding existing tools and hands-on development that combines engineering with AI expertise.
Responsibilities Include:
- Comparative Analysis: Conduct thorough evaluations of commercial solutions (e.g., ABBYY, Adobe, AWS Textract) versus open-source/AI-native alternatives (e.g., Mistral OCR, Docling, Nougat, LlamaParse).
- Benchmarking: Define metrics for
