Amit P.

Senior AI Engineer with 12+ years of experience building AI-powered PDF processing, OCR, Document AI, Document Intelligence, Computer Vision, automation, web applications, backend & data extraction systems using C++, Python and .NET. I help clients solve difficult document-processing problems by developing reliable, cost-effective software for: ✔ AI Automation & Intelligent Workflows ✔ Computer Vision & RAG ✔ PDF Processing, Editing & Conversion ✔ OCR & Document AI (Tesseract, PaddleOCR, Amazon Textract, Google Vision AI) ✔ Intelligent Data Extraction & Automation ✔ Web Applications & Backend APIs ✔ Desktop Applications ✔ High-volume Processing Systems Experience includes: • Enterprise grade Document Convertersion Solutions (eg PDF to Word / Excel / HTML / PPT / Image conversion systems using OpenXML SDK and PDF processing libraries) • OCR workflows for scanned documents • AI-powered extraction from structured & unstructured documents • Layout-preserving document rendering, pdf editing apps & validation • Batch processing and automation systems • Performance optimization of legacy software Tech Stack: C++, C#, Python, TypeScript | .NET, ASP.NET Core, React | PDFium, MuPDF, Apache PDFBox | OpenCV | OCR | WPF | Win32/MFC | SQL | AWS | Docker | Redis | PostgreSQL Why clients work with me: ✔ 12+ Years Experience ✔ 100% Job Success & Top Rated on Upwork ✔ Strong debugging & R&D skills ✔ Focus on cost-effective, maintainable solutions using open-source technologies where suitable ✔ Reliable communication and long-term support If you need help with PDF processing, OCR, Document AI, Computer Vision or custom software development, feel free to reach out.