We are looking for a Python developer to integrate OCR functionality into an existing automated invoice processing pipeline. The current system already handles invoice ingestion and processing. Your task will be to add OCR capabilities so the system can extract text and key invoice data from scanned PDFs and image-based invoices before passing the data to the existing workflow. Requirements:

• Strong Python experience
• Experience with OCR tools such as Tesseract or similar
• Familiarity with PDF and image processing
• Ability to work with existing code and make targeted improvements

Deliverables:

• OCR integration into the current pipeline
• Extraction of invoice text and key fields
• Basic testing to verify accuracy and compatibility with the existing workflow
• Clean, documented code changes

Timeline: This is a small task expected to take approximately 1~2 days to complete. Please include a brief description of your OCR experience when applying.