Senior Python Developer — Parser, OCR and Data Extraction

Description

Develop and evolve the PDF parsing and data extraction engine for electricity bill documents in an environment involving large-scale PDF document processing, OCR, structured parsing, data validation, quality monitoring, and continuous improvement of processing performance and stability. * Develop and maintain PDF document parsers * Create new data extraction models * Evolve OCR and parsing strategies * Fix extraction failures and inconsistencies * Improve processing performance and stability * Work with documents having varied and non-standard layouts * Monitor model quality and error rate * Develop internal tools to support operational and technical activities * Participate in defining technical data extraction strategies * Investigate complex parsing and OCR cases * Handle high-volume document processing * Improve existing pipelines and propose new technical approaches * Directly contribute to the evolution of the processing architecture