Thiago Da Silva
Artificial Intelligence Researcher at Tecgraf / PUC-Rio
Rio de Janeiro, Brazil
Summary
👤
Senior🎓
Top SchoolThiago Da Silva is an applied AI researcher and engineer based in Rio de Janeiro with eight years of experience building computer vision solutions for medical imaging, biometrics, and remote sensing. He is completing dual master's studies at PUC-Rio while leading research projects that range from estimating coronary calcium burden from non-gated chest CTs to developing spatio-temporal diffusion models for forecasting oil slick drift using satellite data. Thiago has productionized CNN-based face recognition and liveness systems, led object-detection deployments for people counting, and implemented MLOps pipelines with TorchServe and model monitoring. Comfortable bridging theory and engineering, he combines strong mathematical tutoring and academic roots with hands-on experience delivering robust inference pipelines in real-world, safety-critical domains. An intriguing thread through his work is applying generative and spatio-temporal modeling to practical problems that blend environmental monitoring and healthcare.
8 years of coding experience
4 years of employment as a software developer
Bacharelado Sistemas Embarcados, Bacharelado Sistemas Embarcados at Télécom ParisPontifical Catholic University of Rio de Janeiro
Portuguese, English, French
Github Skills (97)
sequence-to-sequence10
ctc10
facebook10
sequence10
convolutional-neural-networks9
conformer9
nlp9
smart-city9
python9
deep-learning9
pytorch9
machine-learning9
artificial-intelligence9
transformer-architecture9
computer-vision8
Programming languages (7)
Github contributions (5)
thimabru1010/ResUnet-a_mltsk_keras
Mar 2020 - Apr 2022
Contributions:7 commits, 322 pushes, 11 branches in 2 years
thimabru1010/resuneta
Oct 2020 - Jan 2021
mxnet source code for the resuneta semantic segmentation models
Contributions:544 pushes in 3 months
pytorchmxnetsemantic-segmentationdeep-learningsemantic-segmentation-models
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.