Noah M.

Applied AI Engineer and Backend Developer with 6+ years of experience building production-ready AI systems, scalable backend services, and high-throughput data pipelines. Most recently, I worked as a Senior Applied AI Engineer at JPMorgan Chase, where I helped develop and optimize enterprise-scale RAG (Retrieval-Augmented Generation) systems powering internal LLM analytics platforms. My work included FastAPI backend development, vector database retrieval systems, LangChain-based agents, AWS data pipelines, prompt orchestration, and large-scale document processing workflows handling 40M+ documents. I also have extensive experience in computer vision and real-time AI systems, including developing YOLO-based detection pipelines, OCR systems, spatial tracking systems, and custom ML workflows using PyTorch, TensorFlow, and OpenCV. Core areas I specialize in: • LLM Applications & RAG Systems • AI Agents & Prompt Engineering • FastAPI / Flask Backend Development • Python Automation & API Integration • Computer Vision (YOLO, OpenCV, OCR) • AWS & Cloud Infrastructure • Vector Databases & Embeddings • Data Pipelines & ML Workflows I focus on building clean, scalable, production-quality systems with strong communication and fast iteration cycles. Whether you need an AI-powered application, backend architecture, automation tooling, or computer vision integration, I can help turn ideas into reliable software solutions.