Gabriel Moreira
Machine Learning Engineer at NVIDIA
São José dos Campos, São Paulo, Brazil
Summary
🤩
RockstarGabriel Moreira is a Machine Learning Engineer with 14 years of experience specializing in deep learning for recommender systems, currently contributing as an ML Research Scientist at NVIDIA. Based in São José dos Campos, Brazil, he brings a strong background bridging data science, machine learning engineering, and software engineering across the full ML pipeline. His open-source work on NVIDIA-Merlin's Transformers4Rec focuses on data preprocessing, candidate sampling strategies, and performance-minded data loading—skills that help turn large e-commerce datasets into production-ready training inputs. He has hands-on expertise optimizing memory and throughput for sequential and session-based recommendation models. Known for pragmatic engineering, Gabriel blends research-grade modeling with production reliability to accelerate recommendation quality and serving efficiency. Colleagues rely on him to translate complex sampling and preprocessing requirements into scalable, maintainable implementations.
14 years of coding experience
Stackoverflow
41reputation
468reached
0answers
1question
Github Skills (9)
data-preprocessing10
pandas10
pytorch10
machine-learning10
tensorflow10
hbase6
titan6
google-cloud-bigtable6
bigtable6
Programming languages (5)
Github contributions (5)
NVIDIA-Merlin/Transformers4Rec
Jun 2020 - Dec 2022
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
Role in this project:
Data Scientist & ML Engineer
Data Scientist & ML EngineerContributions:56 reviews, 614 commits, 23 PRs in 2 years 6 months
Contributions summary:Gabriel's commits primarily focused on preprocessing data and preparing it for machine learning tasks within the Transformers4Rec framework. The user implemented and tested candidate sampling strategies, including uniform, recency, recent popularity, and co-occurrence sampling methods. Their contributions involved converting preprocessed e-commerce data into a format suitable for binary classification, as well as refactoring data loading for better performance and optimized memory usage.
xlnetbertlanguage-modelseq2seqrecommendation
gabrielspmoreira/nui4map.net
Apr 2013 - Jun 2013
Contributions:23 commits in 1 month
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.