Python Developer / AI Engineer (Document Processing)

Middle+ Python Developer / AI Engineer for document processing at AYROSA. Remote work, financial document handling, OCR and AI integration.

Responsibilities: - Parse and process documents in Excel, PDF, and scanned formats - Extract tabular data from documents - Normalize dates, document numbers, amounts, and other fields - Design and implement data matching logic - Identify discrepancies between two sources - Handle complex cases: different periods, differing numbers, partial matches, and other ambiguous situations - Integrate OCR and Document AI tools - Use LLM when needed for interpretation and human-readable explanations - Develop backend/API for the service - Participate in MVP architecture design - Work with real anonymized financial documents and test solution quality on historical data

Requirements: - Commercial experience in Python development from 3 years - Strong Python skills - Experience with pandas and tabular data - Experience with Excel/CSV processing - Experience with PDF parsing - Experience in backend services and REST API development - Understanding of matching, normalization, and data cleaning algorithms - Ability to design solutions independently, not just work to a ready-made technical specification - Experience with Git Nice to have: - OCR experience: Tesseract, PaddleOCR, or similar - Experience with PyMuPDF, pdfplumber, Camelot, Tabula - Experience with fuzzy matching - Document AI / Intelligent Document Processing experience - LLM API integration: OpenAI, Azure OpenAI, YandexGPT, or similar - Experience with reconciliation / data matching systems - Experience with financial, accounting, or other structured documents - On-Premise solutions experience - Experience in building solutions combining deterministic business logic and AI

Work format: remote possible