CV

CV#

Professional Experience#

Cielo, Remote — Senior Data Scientist#

01/2025 - Current#

  • Led the development of a cloud data infrastructure on AWS and Databricks using with Git to automate deployments and achieving a 67% improvement in data processing speed.

  • Reduced AWS costs by 75% through monitoring and optimization saving R$1.3M annually.

  • Provided technical leadership in data productization, driving operational KPIs improvement by over 45%.

  • Improved ETL process documentation in AWS by 50% through the use of Git for version control.

  • Implemented machine learning models to optimize the customer service journey, increase KPIs by 45%.

  • Utilized AWS Athena to analyze customer data, which contributed to a 10-point increase in NPS

  • Developed PySpark data pipelines and Data Quality solutions, improving daily indicators by 120%.

  • Promoted best practices in data engineering and machine learning by leading internal technical training.

Itau Unibanco, Remote — Data Engineering#

04/2023 - 01/2025#

  • Led the migration of a legacy system to a modern AWS data platform, engineering an infrastructure with EMR, Lambda, Glue, and Step Functions,implementing CI/CD practices that resulted in a 65% reduction in processing time and annual savings of R$15.7M.

  • Automated manual table loads, reducing load times by 95% using Glue, Step Function and Lambda.

  • Integrated data environments into the public cloud using Linux and SQL, cutting legacy table usage by 93%.

  • Enhanced data quality with scalable solutions using Glue, PySpark, improving integrity and control by 375%.

  • Developed and maintained ETL pipelines for 270+ tables using Glue, EMR, Lambda and Step Functions.

  • Acted as a technical reference for data architecture design, contributing to the development of a strong data-driven culture within the bank.

Itau Unibanco, Remote — Data Scientist,#

06/2021 - 04/2023#

  • Increased product conversion by 250% through classification models, generating an annual R$50M in revenue.

  • Implemented clustering techniques, resulting in a 20% improvement in campaign personalization.

  • Performed bias-variance analysis, model explainability, and overfitting mitigation for credit models.

  • Developed and maintained ETL pipelines for 15+ machine learning models using EMR,Glue and SageMaker.

  • Automated data and machine learning pipelines using Python, PySpark, reducing operational effort by 75%.

Education#

  • University of Sao Paulo, Machine Learning, Computer Vision - MSc, 2026

  • University of Sao Paulo, Software Engineering - MBA, 2026

  • Virtual University of the State of São Paulo, Education - Specialization, 2026

  • University of Sao Paulo, Mechatronics Engineering - BE, 2022

Contents