Osama Makansi
Senior Applied Scientist at Amazon
Wildberg, Baden-Württemberg, Germany
Summary
👤
Senior🎓
Top SchoolOsama Makansi is a Senior Applied Scientist with a decade of experience at the intersection of generative AI and computer vision, currently driving advanced GenAI and multimodal model work at Amazon. He holds a PhD from the University of Freiburg where his research focused on optical flow, unsupervised and semi-supervised learning, robustness, and explainability for autonomous systems. Osama has a track record of moving research into production—spanning internships and multiple applied scientist roles at Amazon—and brings deep expertise in future prediction and uncertainty estimation for video tasks. Based in Wildberg, Germany, he combines rigorous academic training with hands-on engineering across large-scale ML systems, and often applies classical vision insights to improve modern deep learning pipelines.
10 years of coding experience
9 years of employment as a software developer
Phd, Informatik, Phd, Informatik at The University of FreiburgBachelor of Engineering (BEng), Informatics Engineering, Bachelor of Engineering (BEng), Informatics Engineering at Jami't Alep
Arabic, English, German
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (32)
heterogeneous8
autonomous-driving8
traffic8
trajectory-generation8
multimodal-deep-learning8
random-walk7
localization7
prediction7
paper6
graph-convolutional-networks5
computer-vision5
deep-learning5
autonomous-vehicles5
multimodal5
machine-learning5
Programming languages (3)
Github contributions (5)
lmb-freiburg/FLN-EPN-RPN
Jun 2020 - Dec 2020
This repository contains the source code of the CVPR 2020 paper: "Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior"
Contributions:3 commits, 3 pushes, 1 branch in 6 months
localizationmultimodal
lmb-freiburg/Multimodal-Future-Prediction
May 2020 - Jan 2021
The official repository for the CVPR 2019 paper "Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction"
Contributions:8 commits, 10 pushes, 25 comments in 7 months
multimodaltrajectory-predictionmultimodal-deep-learning
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.