About

We are seeking an AI Engineer/Expert to design, develop, and implement an OCR + LLM based automation system from scratch. This role requires building the full solution end-to-end , with a focus on automating document processing workflows, integrating OCR with large language models, and leveraging AI agents and generative AI. The position is hands-on, requiring strong development skills, technical ownership, and the ability to deliver working systems. Commitment is 15–20 hours per week. Responsibilities ================================================= 1. Design and implement OCR + LLM pipelines for document automation from the ground up. 2. Build scalable and reliable workflows to handle diverse and complex document layouts. 3. Integrate OCR to extract structured data from clinical documents. 4. Develop, test, and deploy AI models and integrations using Python and modern AI frameworks. 5. Optimize system performance, accuracy, and cost efficiency. 6.Integrate cloud services into the solution. 7. Mentor and provide technical guidance to Team. 8. Own the entire development lifecycle, from implementation to production deployment. Requirements =============================================== 1. Strong proficiency in Python with proven hands-on development experience. 2. Expertise in OCR tools (Tesseract, EasyOCR, AWS Textract, etc.) and integrating them into workflows. 3. Experience working with Large Language Models (LLMs) and generative AI. 4.Demonstrated ability to build AI systems from scratch 5. Familiarity with cloud platforms and scalable infrastructure. 6. Ability to work with complex, multi-layout documents. 7. Strong problem-solving skills and ability to work independently.