André Vieiraesilva
AI Project Lead at Revelo
Pernambuco, Brazil
Summary
👤
Senior🎓
Top SchoolAndré Vieiraesilva is an AI Project Lead and computer vision expert with a decade of experience applying state-of-the-art research to production systems. He holds a PhD in Computer Science and an MSc focused on fluid simulation, and has led research and engineering teams across academia and industry in Brazil and Germany. Known for translating CVPR/ECCV/ICCV research into deployable solutions, he has driven cloud-cost optimizations (GPU→CPU) through model quantization, pruning, ONNX/TensorRT conversions and delivered a NeurIPS ’24 workshop paper from industry work. He has deep hands-on experience in biometrics, embedding alignment, anomaly detection with attention mechanisms, and visual inspection systems. Beyond coding, André excels at technical mentorship, high-quality code review, and organizing major community events like the Latinx in CV workshop at CVPR. An uncommon combination of rigorous PhD research and practical product cost optimization makes him effective at turning novel ML ideas into efficient, real-world systems.
10 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Universidade Federal de PernambucoVisiting PhD student Computer Science, Visiting PhD student Computer Science at Technische Universität Chemnitz
Portuguese, English
Stackoverflow
11reputation
0reached
1answer
0questions
Github Skills (38)
object-tracking10
pytorch10
tower10
high-resolution10
python10
image-classification10
semantic-segmentation10
machine-learning10
yolov810
deep-learning10
instance-segmentation10
pose-estimation10
object-detection10
computer-vision10
ultralytics10
Programming languages (2)
Github contributions (5)
andreluizbvs/VoxarMPS
Aug 2019 - Feb 2021
A fluid simulation system based on the MPS method
Contributions:3 reviews, 32 commits, 1 PR in 1 year 6 months
fluid-simulationvoxarmpsvoxarmpsgpu
andreluizbvs/PLAD
Aug 2021 - Jun 2022
STN PLAD: A Dataset for Multi-Size Power Line Assets Detection in High-Resolution UAV Images
Contributions:1 release, 29 commits, 28 pushes in 10 months
datasetobject-detectiondeep-learningpowerlineshigh-resolution
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.