Matheus Leite

I am an AI Engineer specializing in the end-to-end development of Agentic AI systems and advanced Retrieval-Augmented Generation (RAG) architectures. My current focus involves engineering stateful workflows using LangChain and LangGraph, where I integrate Weaviate vector storage and Sentence-Transformers CrossEncoders to achieve high-precision information retrieval. I have successfully led projects that automated complex document analysis processes, resulting in 50% efficiency gains by implementing Corrective RAG strategies and Human-in-the-Loop validation mechanisms.

• Beyond architectural design, I possess strong capabilities in building robust, tool-using AI agents that handle file management, data sanitization, and workflow orchestration. I ensure system reliability by implementing structured outputs using Pydantic models. My technical stack is grounded in Python, SQL, and Docker, with practical experience deploying solutions on Google Cloud Platform (GCP). Furthermore, my background extends to Big Data engineering, demonstrated by my work developing real-time recommender systems utilizing Spark Streaming and Kafka. I combine these technical skills with Agile methodologies to drive projects from 3D modeling and simulation to full-scale AI deployment, ensuring both innovation and operational excellence.