Hello, I'm

João Manoel Herrera
Pinheiro

Senior Data Engineer & PhD Candidate

77 Citations
10 Publications
João Manoel Herrera Pinheiro
SP, Brazil

About Me

Senior Data Engineer and Data Scientist with over 5 years of experience in the banking and technology sectors, including significant tenures at major LATAM institutions like Itaú Unibanco and Cielo. I specialize in architecting scalable machine learning systems and high-performance data engineering pipelines within cloud-native environments.

Currently pursuing a D.Sc. (PhD) in Electrical Engineering, my research focuses on Computer Vision, Machine Learning, and Image Processing. Alongside my studies, I serve as a lecturer in AI and Computer Vision. My academic work has been published in premier journals, including IEEE and Nature.

Research Interests

Computer Vision Deep Learning Machine Learning Artificial Intelligence Image Preprocessing Medical Image Robotics Data Engineer

Professional Experience

Senior Data Engineer

Cielo S.A Jan 2025 ‐ Present

• Led Data Engineering and Architecture for Customer Service, owning a large-scale AWS and Databricks platform supporting IVR, WhatsApp, and ML-driven analytics.

• Reduced AWS infrastructure costs by 75% ($1.3M) through workload optimization and monitoring.

Data Engineer & Data Scientist

Itaú Unibanco S.A Jun 2021 ‐ Jan 2025

• Led migration of a high-volume financial data platform from Teradata to AWS (EMR, Glue, Lambda, Step Functions), reducing processing time by 78% and saving $3.2M annually.

• Developed ML models for CRM and financial product recommendation at 100M+ scale, increasing conversion by 250% and generating $9.3M/year.

Researcher

USP Jul 2023 ‐ Present

• Leading research on projects with a budget exceeding R$48 million acting as Specialist in Machine Learning, Computer Vision and Cloud Computing.

• Supervising and mentoring 10+ undergraduate and master's students in research activities related to computer vision, medical imaging, and robotics.

• Computer Vision Professor for a class of approximately 30 undergraduate students.

Education

Master of Business Administration ‐ MBA, Specialization in Software Engineering

University of Sao Paulo (USP)

Oct 2024 ‐ June 2026

GPA 9.92/10

Specialization in Education

UNIVESP

July 2024 ‐ July 2026

GPA 9.9/10

Bachelor of Engineering ‐ BE in Mechatronics, Robotics

University of Sao Paulo (USP)

Feb 2016 ‐ Dec 2022

Selected Publications

Google Scholar · ORCID ‐ 77+ citations · h-index: 4 · i10-index: 1

2026

Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI

Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, ..., Marcelo Becker

ArXiv preprint

2026

Descriptor: Parasitoid Wasps and Associated Hymenoptera Dataset (DAPWH)

Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, ... , Marcelo Becker

IEEE Data Descriptions

2026

A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation

Thiago H. Segreto, ... João Manoel Herrera Pinheiro, Ricardo V.Godoy, Marcelo Becker

Nature Scientific Data

5
2025

The impact of feature scaling in machine learning: Effects on regression and classification tasks

João Manoel Herrera Pinheiro, Suzana Vilas Boas de Oliveira, Thiago Henrique Segreto Silva, Pedro Antonio Rabelo Saraiva, Enzo Ferreira de Souza, Ricardo V Godoy, Leonardo André Ambrosio, Marcelo Becker

IEEE Access

60
2025

A Synthetic Dataset for Manometry Recognition in Robotic Applications

Pedro Antonio Rabelo Saraiva, Enzo Ferreira de Souza, João Manoel Herrera Pinheiro, ... , Marcelo Becker

IEEE LARS 2025

1

Technical Skills

Data Science & ML

Python
TensorFlow & PyTorch
scikit-learn & NumPy
OpenCV & TorchVision
Pandas, SciPy & Optuna

Data Engineering

PySpark & Apache Spark
SQL (Presto & Hive)
ETL & Data Pipelines & Big Data
Data Lake & Data Warehouse
Scala & Data Products

Tools & Cloud

AWS (EMR, Glue, Lambda, Step Functions)
Databricks & Snowflake
DevOps (Docker, CI/CD, Git, GitHub)
Terraform & Linux
LaTeX & Markdown

Research Domains

Computer Vision Deep Learning Machine Learning Artificial Intelligence Image Processing Object Detection Semantic Segmentation Biomedical Engineering Robotics

Projects

2001 Engenharia

2001 Engenharia

YouTube channel that aims to teach courses in technology and engineering with more than 150 Videos and 500K Views.

bibliotheca

bibliotheca

My automated personal library inventory system featuring Cutter-Sanborn classification and automated metadata enrichment using GitHub, Google API.

Get in Touch

Open to international opportunities and research collaborations.