Deepak Kandel
Graduate Research Assistant
City of Rochester, New York, United States
Summary
👤
Senior🎓
Top SchoolDeepak Kandel is a PhD candidate and graduate research assistant at Rochester Institute of Technology with eight years of experience applying Bayesian and variational inference methods to real-world computer vision problems. He focuses on developing novel algorithms for uncertainty estimation, self-awareness, and continual/lifelong learning for streaming data, bridging rigorous research with practical imaging applications. Prior industry roles span medical image segmentation, OCR-driven document digitization, demand forecasting, and recommendation systems, showing a strong track record of moving models into production. As a former GTA, he also teaches probability, statistics, and imaging science, combining pedagogy with hands-on engineering. Based in Rochester, NY, he brings a rare mix of theoretical depth and applied ML experience, including migrating complex codebases between major frameworks and tuning parameter-efficient finetuning for specialized medical tasks.
8 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy - PhD, Imaging Science, Doctor of Philosophy - PhD, Imaging Science at Rochester Institute of TechnologyBachelor of Engineering - BE, Computer Science, First Division, Bachelor of Engineering - BE, Computer Science, First Division at Tribhuvan University, IOE, Pulchowk Campus
Github Skills (40)
github-issues10
github10
python10
programming-language9
deep-learning8
information-theory8
gpu8
machine-learning8
memory-efficient7
r7
meta-learning7
forecast7
transfer-learning7
vscode6
philosophy6
Programming languages (4)
Github contributions (5)
kandeldeepak46/Keep-Learning
Dec 2020 - Jan 2023
Contributions:406 commits, 389 pushes, 1 branch in 2 years 1 month
kandeldeepak46/Image-Classification-And-Object-Localization-ImageNet-Keras
Feb 2021 - Sep 2022
Contributions:20 commits, 17 pushes, 1 branch in 1 year 7 months
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.