I’m a Applied AI Engineer with over 10 years of experience delivering data-driven applications and AI-powered systems across industries. I specialize in Retrieval-Augmented Generation (RAG), back-end development, and LLM-based architectures, helping companies turn raw data into actionable intelligence through scalable, production-ready solutions.
I’ve worked with companies in both Brazil and the United States, delivering AI products that go far beyond prototypes. From LLM fine-tuning and vector search optimization to integrating AI into mission-critical systems, I focus on building things that actually ship.
This blog is a place where I share what I’ve learned, not from theory, but from the real trenches of AI engineering.
My Focus
💻 Applied Machine Learning & Back-End Engineering
🤖 GenAI, LangChain, RAG, Vector Search and Prompt Optimization
🧠 Scaling LLM systems with LangGraph, LangSmith, Hugging Face and more
🧰 Building high-performance pipelines with FastAPI, Docker, Kubernetes and more
🔍 Communicating complex systems clearly for both technical and business stakeholders
Experience Snapshot
I currently work for U.S. based companies, developing scalable RAG systems, deploying containerized LLM solutions, and integrating GenAI into real-world product lines. I previously led GenAI initiatives at large-scale organizations, delivering production-grade AI systems that improved decision-making, recommendation engines, and internal automation.
Before diving deep into AI architecture, I worked as a Senior Data Scientist in roles involving forecasting, analytics, and data storytelling, experience that shaped my pragmatic, impact-driven approach to building systems.
