██████╗  █████╗ ████████╗██████╗ ██╗   ██╗ ██████╗██╗  ██╗
██╔══██╗██╔══██╗╚══██╔══╝██╔══██╗╚██╗ ██╔╝██╔════╝██║ ██╔╝
██████╔╝███████║   ██║   ██████╔╝ ╚████╔╝ ██║     █████╔╝ 
██╔═══╝ ██╔══██║   ██║   ██╔══██╗  ╚██╔╝  ██║     ██╔═██╗ 
██║     ██║  ██║   ██║   ██║  ██║   ██║   ╚██████╗██║  ██╗
╚═╝     ╚═╝  ╚═╝   ╚═╝   ╚═╝  ╚═╝   ╚═╝    ╚═════╝╚═╝  ╚═╝

Analytics Engineer — risk modeling, big data, and the space where ML meets production

5 years in fraud prevention at iFood — Latin America's largest food delivery platform.
Started in analytics and KPIs, migrated into data science and MLOps as the problems
outgrew dashboards. Now I build risk scoring models on billion-row datasets,
deploy them to production, and make sure they're explainable — not just accurate.

┌──────────────────────────┬──────────────────────────┬──────────────────────────┐
│       RISK MODELING      │      MLOPS & INFRA       │     EXPERIMENTATION      │
├──────────────────────────┼──────────────────────────┼──────────────────────────┤
│                          │                          │                          │
│  ▸ Fraud risk scoring    │  ▸ PySpark · Databricks  │  ▸ EBM · Bayesian think  │
│  ▸ Statistical modeling  │  ▸ Airflow pipelines     │  ▸ Model explainability  │
│  ▸ Big data (B+ rows)    │  ▸ SageMaker endpoints   │  ▸ A/B testing           │
│  ▸ Feature engineering   │  ▸ DAB (asset bundles)   │  ▸ Quantified workflows  │
│  ▸ Anomaly detection     │  ▸ S3 · IAM · AWS stack  │  ▸ Agent-native tooling  │
│                          │                          │                          │
└──────────────────────────┴──────────────────────────┴──────────────────────────┘

🇧🇷 Fortaleza(CE), Brasil