Gabriel Soares is a Senior Machine Learning Engineer with nine years of experience building production-grade ML platforms and real-time fraud prevention systems, currently driving fraud scoring and ONNX model serving at Teya. He combines cloud-native ML (SageMaker, Kubernetes, SageMaker Pipelines) with streaming feature engineering (Apache Flink) and robust microservices in Golang to deliver low-latency, high-throughput payment risk pipelines. His background spans fintech and scale-ups—Nubank, BTG Pactual, CargoX—where he automated data ingestion, CI/CD, and model lifecycle monitoring using tools like Airflow, MLflow, and Kubeflow. As an instructor at Tera he translates complex ML concepts into business-facing courses, reflecting a talent for teaching as well as engineering. Uncommonly, Gabriel began his career as a geologist, bringing statistical thinking from geoscience and remote sensing into data-driven model design and feature engineering. He is based in Porto, Portugal, and known for pragmatically marrying research-grade models with operational reliability.
9 years of coding experience
7 years of employment as a software developer
Data Science & Machine Learning for Business, Inteligência Artificial, Data Science & Machine Learning for Business, Inteligência Artificial at Tera
Bacharelado em Geologia, Geologia/Ciências da Terra, Geologia e Ciências da Terra/Geociências, Bacharelado em Geologia, Geologia/Ciências da Terra, Geologia e Ciências da Terra/Geociências at USP - Universidade de São Paulo
Bachelor’s Degree, System Analysis and Development, Bachelor’s Degree, System Analysis and Development at Faculdade de Tecnologia de São Paulo - FATEC-SP
Contributions:31 commits, 5 PRs, 10 pushes in 7 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.