About the job
About Us:
TransPerfect, a globally recognized leader in translation software, embodies a dynamic start-up culture and is on the lookout for a talented and enthusiastic Backend Developer to join our pioneering Artificial Intelligence (AI) team. This is your chance to influence the trajectory of AI within a world-class organization. Over the past decade, our AI team has evolved into a key player in advancing machine translation, generative AI, natural language processing, and automation.
We are in search of a skilled backend developer who is eager to explore the forefront of technology and make a significant impact in the AI domain. Join a diverse global team of professionals across the USA, Spain, Portugal, and India. If you are driven by the creation of robust and scalable AI solutions, this is an ideal opportunity for you.
About the Role:
As a Backend Developer, your primary focus will be on tackling the final stages of document processing: transforming intricate, unstructured PDFs into neatly formatted, editable .docx files. Our goal transcends mere text extraction; we aim to faithfully reproduce the visual and structural intent of the original document, including nested tables, multi-column layouts, font hierarchies, and styling.
In this hybrid role, you will spearhead the research and development of our document conversion pipeline, necessitating both strategic oversight (keeping abreast of existing tools) and hands-on coding (melding engineering and AI expertise).
Your responsibilities will include:
- Comparative Analysis: Conduct a thorough evaluation of commercial solutions (ABBYY, Adobe, AWS Textract) versus open-source/AI-native alternatives (Mistral OCR, Docling, Nougat, LlamaParse).
- Benchmarking: Define metrics for
