I am a Data Science student at FATEC Jundiaí focusing on Data Engineering, Machine Learning, and database systems. I build end-to-end data pipelines, RAG systems, and data warehouses with a strong commitment to clean architecture and code quality.
- Languages: Python, SQL, R, JavaScript, HTML, CSS
- APIs & Backend: FastAPI, Celery, Redis
- Database & DW: PostgreSQL, DuckDB, Databricks, Apache Spark (PySpark)
- Machine Learning & AI: scikit-learn, PyTorch, Transformers (TrOCR), Gemini API
- DevOps: Docker, Nginx, GitHub Actions (CI/CD)
- Environments: Jupyter Notebook, RStudio, POSIT
- fiscaliza-jundiai: Public data pipeline and transparency dashboard built with FastAPI, Celery, and PostgreSQL. Handles Bronze/Silver/Gold data layers and financial reconciliation.
- docmind-rag-assistant: Retrieval-Augmented Generation (RAG) backend utilizing FastAPI, FAISS, and the Gemini API for semantic search over technical documents.
- energy-sustainability-dw: A dimensional Data Warehouse built using DuckDB and SQL to analyze the global energy transition.
- paleographia-htr: A deep learning Handwritten Text Recognition (HTR) system based on TrOCR to transcribe historical manuscripts.
Sou estudante de Ciência de Dados na FATEC Jundiaí com foco em Engenharia de Dados, Aprendizado de Máquina e sistemas de banco de dados. Desenvolvo pipelines de dados de ponta a ponta, sistemas RAG e armazéns de dados dimensionais (DW) com compromisso com arquitetura limpa e qualidade de código.
Connect with me on LinkedIn (or check my repositories below).