Cost-Aware Fabric Implementation
Architecting a Lakehouse for 30+ production tables.
Replaced resource-heavy Dataflows with high-performance PySpark notebooks to stay within F2-SKU (low cost) limits without losing stability.
Senior Data & AI Engineer specializing in cost-aware architectures. I bridge the gap between complex Data Engineering and Agentic AI, building systems designed for performance, scale, and long-term maintainability.
Learn SQL the way professionals use it
Master SQL through real analytical challenges. Work with authentic business datasets, uncover insights, and improve your skills with instant feedback, guided hints, and immersive scenarios inspired by real corporate challenges.
Real-world architectural decisions balancing performance, cost, and maintainability.
Architecting a Lakehouse for 30+ production tables.
Replaced resource-heavy Dataflows with high-performance PySpark notebooks to stay within F2-SKU (low cost) limits without losing stability.
SAP HANA to Oracle migration with 100M+ records.
Developed a custom Python framework using multiprocessing/threading. Prioritized throughput and data consistency for massive volumes over using generic, slower ETL tools.
Orchestrating complex workflows (ticketing/resets) for a transportation conglomerate.
Implemented LangGraph for multi-agent logic instead of simple linear bots. A system capable of real-world reasoning and autonomous task execution via REST APIs.
Independent SaaS products built to solve real-world problems.
AI-powered platform for B2B procurement professionals. Create RFP/RFQ/RFI documents with interactive editing, real-time quality analysis, and professional PDF/DOCX exports.
KPI engineering platform that transforms data into strategic clarity. Features natural language intent definition and 75+ curated strategic KPIs for dashboard blueprinting.
LPG price comparison platform for Brazil. Find the cheapest gas stations with statistical analysis, savings calculations, and community-driven price reporting.
Open source contributions and personal projects showcasing engineering decisions.
Repo template para projeto de Engenharia de Dados
An intelligent, automated system for generating and testing pandas data cleaning pipelines using AI agents and structured quality checklists.
feat: complete agent system with English translations and improved documentation
This is an Awesome List with materials and resources to the developers who wants to spread the Word of God using Technology developing something useful.
Repo código da página simples do "Gás Mais Barato"
Framework de Data Warehouse single-node para pipelines ETL com conectores de origem e destino.
A "one-click" data diagnostic tool that ingests raw datasets, runs automated cleaning, computes KPIs, and uses an LLM to turn cold metrics into a concise business narrative.
**Article Scout** is an intelligent research paper evaluation system that helps students and researchers assess the relevance and quality of academic papers for their TCC (Final Project) or research w
feat: Complete project restructuring and documentation overhaul
This is an inredible agent helper for It support department in companies
Projeto de Analytics voltado para Gestão de Pessoas (Executivo Federal) - Cargos Vagos e Vacâncias
A WhatsApp chatbot for medical appointment scheduling using natural language, integrated with Google Calendar and designed for easy scalability across multiple doctors and clinics.
feat: complete MediNow WhatsApp medical bot with Docker setup
Programa para Exegese/estudo bíblico com consulta de versículos e estudos de palavras em pc local.
Template para criar chatbots e agentes de IA com suporte a múltiplos provedores de LLM e canais de mensagem.
Projeto CrewAI Data Warehouse - Automação na Construção de Data Warehouses Open Source
Welcome to The Pipeline Creators, a robust and modular framework for designing, implementing, and testing data engineering pipelines. This project leverages the power of Pandas, Pydantic, and Pytest t
Projeto para aplicação de conceitos SQL Pílulas: Laboratório de Data Quality & Fuzzy Matching
feat: Add comprehensive README with setup instructions and project overview
Projeto simples de treinamento de fine tunning de modelo llama com 1B conteúdo de AI Engineering
Agente sistema de Compras ERP
Meu primeiro exercício pessoal de aplicação do modelo regressão Linear em Python em Ciencia de dados
Practical Study Case on ENEM Data Open Source
This is an repo to learn bash and linux for Data Engineering
Repositório com a finalidade de registrar um estudo de benchmark de frameworks Pyspark e DuckDB usando dentro do notebook no MS Fabric
This project is a fully local AI-powered blog post generator, using CrewAI to simulate a multi-agent system for researching and writing AI news content.
Este projeto implementa um sistema de análise de qualidade de dados usando crewAI. O objetivo é gerar relatórios técnicos detalhados para arquivos CSV, identificando problemas de qualidade e oferecend
Repo with an use case to understand how to create scalable pipelines
Novo projeto de bot agêntico que tem propósito de ativamente entrar em contato com devedores e negociar/resolver as dívidas
Novo app rapido cujo propósito é brincar com alucinações conforme LLMs o fazem
fix: Include data folder in Docker container
Projeto de Agente de Renegociação e Cobrança Digital B2B
Repo to help create VM on providers via python and terraform
Projeto de automação para apoiar candidaturas técnicas no Linkedin com LangGraph Agents
Repositório padrão de framework para auxilio em migrações de bancos de dados estáticos
Pagina principal do meu Github Profile
Este projeto é um resultado de aprendizado via transmissão no Youtube realizado no dia 23/10/2025.
Repositório único de Queries SQL para usos diversos no trabalho.
An repo only to udnerstaind embeddings
An intelligent RAG (Retrieval-Augmented Generation) agent built with LangGraph, designed to serve as a productivity optimizer for data engineers. By leveraging PySpark documentation and community link
This is my first restaurant website. One page of HTML and CSS fundamentals
Repositório criado para criação das mais diversas funções no python a fim de dominar o tema.
Repositório dos arquivos que representam todo o projeto público que consiste em trazer dados de Compras Públicas do Governo Federal e fazer análises
Repo para praticar modelos de time series em jupiter notebook
A little example of a dashboard created with plotly and dash (python)
Api para requsições de CEP em Python
Criação de novo site durante o curso de Git e Github
Meu primeiro repositório aula Git e Github
A robot powered training repository :robot:
fix: Gemfile & Gemfile.lock to reduce vulnerabilities
Last synced: April 26, 2026 at 7:30 PM
Articles on RAG, LLM, and AI engineering — with book references and code.
How to set chunk size, overlap, and dual indexing (embedding + tsvector) to maximize recall in production RAG pipelines — with Python code and real tradeoffs.
How to combine vector search and keyword retrieval for precise technical context in production RAG pipelines.
5+
years experience
100M+
records migrated
30+
production tables
5
certifications
Key roles in Data Engineering and AI Automation
SCORAS
NINECON
BLUER TECNOLOGIA
AB INBEV (via Peapply Consulting)
IBM (Client: Vale)
Technologies and paradigms I work with daily.
Microsoft Fabric Data Engineering Associate
DP-700
Azure Fundamentals
AZ-900
Azure Data Fundamentals
DP-900
Oracle Cloud Infrastructure Associate
OCI
Oracle AI Agent Associate
Oracle
MBA in Logistics Engineering
Faculdade Porto das Monções | 2014-2017
Bachelor's Degree in Logistics
Faculdade Porto das Monções | 2011-2013
Data Analytics Training (300+ hours)
Alura | 2021-2022