Role : Senior AI/ML Engineer Location: Woodland Hills, CA & Mason, OH FTE Salary - $160k/Annum Job Description Must Have Technical/Functional Skill We are looking for a highly skilled Python Developer with strong experience in FastAPI, LangChain, LangGraph, and OCR technologies (Tesseract). The role involves building scalable APIs, orchestrating LLM-based workflows, and implementing document ingestion and text extraction pipelines to support AI-driven applications. Key Skills • Strong proficiency in Python. • Hands-on experience with FastAPI for backend/API development. • Practical experience with LangChain for LLM orchestration and integrations. • Experience using LangGraph for managing complex AI workflows and stateful executions. • Experience with Tesseract OCR for text extraction from scanned documents and images. • Good understanding of REST APIs, asynchronous processing, and microservices architecture. • Experience working with structured and unstructured data. Good to Have • Exposure to OpenAI / Azure OpenAI / other LLM platforms. • Experience with document processing pipelines (PDFs, images, scanned files). • Familiarity with containerization tools (Docker) and cloud platforms. • Knowledge of vector databases and embeddings. • 4–8 years of overall backend or Python development experience. • Proven experience delivering production-ready AI or document-processing solutions. Roles & Responsibilities • Design, develop, and maintain RESTful APIs using Python and FastAPI. • Build and orchestrate LLM-based workflows using LangChain and LangGraph. • Integrate Tesseract OCR for document scanning, text extraction, and preprocessing from images and PDFs. • Develop backend services for AI/ML-driven use cases, focusing on performance and scalability. • Implement prompt workflows, agents, and state graphs for complex AI reasoning pipelines. • Collaborate with data scientists, ML engineers, and frontend teams to deliver end-to-end solutions. • Ensure code quality through unit testing, code reviews, and documentation. • Optimize APIs and processing pipelines for speed, reliability, and accuracy.