Summary
Yuval Levental is a machine learning engineer and patent examiner with eight years of experience applying deep learning to complex 3D data, from lidar forest segmentation to thermal imaging for medical diagnostics. With an MS in Imaging Science from RIT and a BS in Electrical Engineering, he bridges rigorous experimental design and practical software delivery, building evaluation pipelines and production-ready models in Python, PyTorch, and C++. At the USPTO he pairs technical depth with clear, auditable decision-making, drafting detailed office actions that reflect strong analytical judgment. His research work includes novel 3D convolutional approaches for voxelized lidar and point-cloud reconstruction, and he has hands-on experience turning noisy thermal data into clinically useful 3D models. Colleagues cite his passion for rigorous measurement and reliability—he focuses on ML systems that not only perform well in experiments but behave predictably in real-world deployments.
8 years of coding experience
3 years of employment as a software developer
Master of Science - MS, Imaging Science, Master of Science - MS, Imaging Science at Rochester Institute of Technology
Bachelor of Science - BS, Electrical Engineering, Bachelor of Science - BS, Electrical Engineering at Michigan State University
English