Skip to content
View aj1no's full-sized avatar
3 followers · 5 following

Block or report aj1no

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
aj1no/README.md

Rodolfo Vinicius Cima Takemoto

Ler em Português

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.

Technical Stack

Languages & Frameworks

  • 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

Tools & DevOps

  • DevOps: Docker, Nginx, GitHub Actions (CI/CD)
  • Environments: Jupyter Notebook, RStudio, POSIT

Featured Projects

  • 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.

Sobre Mim (PT-BR)

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).

Pinned Loading

  1. fiscaliza-jundiai fiscaliza-jundiai Public

    Public data pipeline with FastAPI, Celery, and PostgreSQL for collecting, normalizing (Bronze/Silver/Gold), and reconciling financial data from Jundiaí/SP.

    Python 1

  2. energy-sustainability-dw energy-sustainability-dw Public

    A complete dimensional Data Warehouse with DuckDB, SQL, and Python for historical analysis of the global energy transition.

    HTML 1

  3. docmind-rag-assistant docmind-rag-assistant Public

    RAG (Retrieval-Augmented Generation) backend with FastAPI and FAISS for semantic search and question answering over technical documentation.

    Python

  4. datacenter-efficiency-eda datacenter-efficiency-eda Public

    Exploratory Data Analysis (EDA) in Python exploring the correlation between workload, temperature, and energy efficiency in Data Centers.

    Python

  5. islp-machine-learning islp-machine-learning Public

    Solved classification and regression exercises based on the Introduction to Statistical Learning with Python (ISLP) book.

    Python

  6. paleographia-htr paleographia-htr Public

    PaleographIA: An AI-driven Handwritten Text Recognition (HTR) system based on TrOCR for transcribing historical documents from Jundiaí/SP.

    Python