Senior Technical Consultant Required – OCR, AI Data Extraction & .NET Core Integration

We are looking for an experienced Senior Technical Consultant (Individual Freelancer or Agency) to work with our in-house development team for building an intelligent document processing module. The objective of this assignment is to extract structured information from unstructured Purchase Orders (POs) and medical reports, automatically map the extracted data, and populate our existing Angular-based web application. Project Scope The selected consultant will be responsible for designing, developing, integrating, and optimizing an AI-powered document extraction module using open-source technologies. The proposed technology stack includes: -.NET Core for backend processing -Angular (existing application) -Tesseract OCR and/or PDF-Extract-Kit for document -parsing -Ollama running locally -Llama 3, Mistral, or equivalent open-source LLMs for ----intelligent field mapping -REST APIs for seamless integration Responsibilities -Analyze various Purchase Order and medical report formats. -Design an OCR and AI-based extraction pipeline. -Extract text from scanned PDFs, images, and digital PDF documents. -Build intelligent field mapping using open-source LLMs. -Automatically populate Angular forms with extracted values. -Develop scalable and reusable .NET Core APIs. -Optimize extraction accuracy, speed, and reliability. -Handle multi-page and complex document layouts. -Implement validation, confidence scoring, and exception handling. -Work closely with our in-house development team during implementation. -Integrate the module into our existing enterprise application. -Prepare technical documentation, architecture diagrams, and deployment guidelines. -Conduct knowledge transfer and provide hands-on training to our internal technical team. Required Skills -3–5+ years of experience in .NET Core development. -Strong experience with OCR technologies such as Tesseract or similar open-source engines. -Experience with PDF parsing frameworks (PDF-Extract-Kit or equivalent). -Experience with local LLM deployment using Ollama. -Hands-on knowledge of Llama 3, Mistral, or other open-source language models. -Experience in AI-based document understanding and data extraction. -REST API development and system integration. -Angular integration experience. -Strong debugging and performance optimization skills. Preferred Qualifications -Prior experience developing Intelligent Document -Processing (IDP) solutions. -Experience with Purchase Order automation, invoice ----processing, or healthcare document extraction. -Knowledge of prompt engineering and LLM optimization. -Experience working with enterprise applications and secure on-premise deployments. Deliverables -Fully functional OCR and AI-powered extraction module. -Integration with our existing Angular and .NET Core application. -Source code with proper documentation. -Deployment support. -Knowledge transfer and technical training for our internal team. -Support during implementation and bug fixing after deployment. Selection Criteria -Minimum 3–5 years of relevant experience. -Demonstrated experience in OCR, AI, .NET Core, and LLM-based document processing. -Portfolio or case studies of similar implementations. -Strong communication skills and ability to collaborate with our internal development team. If you have successfully implemented AI-powered document extraction systems using open-source technologies and have hands-on experience with OCR, .NET Core, Angular, and local LLMs, we would be pleased to review your proposal.