Data Scientist & AI Engineer Brazil

AI and data systems that hold up in production.

LLMs · RAG · Databricks · Airflow · Machine learning · Python

View my work Let's connect

Open to remote opportunities

Illustrated portrait of Micaelly: red hair, round glasses and a cream cardigan, hugging a small dark-brown dog
4+
years in data & AI
~8M
bank members served by my pipelines
USP
MBA, Data Science + published paper
8
companies and public bodies in data & tech

Work

Selected projects

Journal article · MBA thesis, USP/Esalq

Previsão do Cumprimento da Lei de Responsabilidade Fiscal por Municípios do Mato Grosso utilizando Random Forest
Micaelly Cristine de Moura Santos

Random ForestIBGE · TCE-MT · 2017-2022

Research · Machine learning

Published paper: predicting fiscal-law compliance in Mato Grosso

  • Python
  • Scraping
  • scikit-learn
  • Random Forest

Python · Automation · 2026

A gate that blocks incomplete ad briefs before production

  • Python
  • 22 tests
  • $0 LLM cost

Data engineering

YouTube analytics pipeline, scheduled daily with Airflow

  • Python
  • Airflow
  • Pandas
  • SQL

Career

Experience

  1. Since 2026

    Data Scientist · Prysmo

    LLM + RAG apps in production; Databricks & Airflow pipelines

  2. 2025

    Python Developer · Risk3

    Scrapers that replaced manual data collection for credit analysis

  3. 2024-2025

    Data Engineer · Tech6 Group

    Finance pipelines for a bank with ~8M members; Power BI

  4. 2024

    Innovation Analyst (CNPq fellow) · SOFTEX

    ICT-industry dashboards and research articles

  5. 2024

    Data Science Tutor · EBAC

    Taught Python, SQL and machine learning

  6. 2023-2024

    Back-End Developer · Seno

    Flask REST APIs with OAuth2, in Docker

  7. 2022-2024

    PL/SQL Developer · SEPLAG-MT

    Oracle PL/SQL for Mato Grosso's state personnel system

  8. 2022-2023

    Data Analyst / Engineer · Frexco

    AWS Glue ETL that ended manual CRM extractions

Skills

AI
  • LLMs
  • RAG
  • Embeddings
  • Semantic search
Data
  • Python
  • PySpark
  • SQL
  • Databricks
  • Airflow
  • AWS Glue
  • Oracle PL/SQL
ML & BI
  • scikit-learn
  • Pandas
  • Power BI
  • Metabase
Backend
  • Flask
  • FastAPI
  • PostgreSQL
  • Docker
  • CI/CD

Education

  1. MBA, Data Science & AnalyticsUSP/Esalq · 2024
  2. Systems Analysis & DevelopmentUniFCV · 2024
  3. EconomicsUFMT · 2020

Portuguese (native) · English (professional)