Arvind Vepa
Teaching Assistant at University of California, Los Angeles
Irvine, California, United States
Summary
👤
Senior🎓
Top SchoolArvind Vepa is a research scientist and ML engineer with nine years of experience building label-efficient multimodal AI systems for healthcare, currently at Meta after doctoral work at UCLA. He combines deep technical skills in Python, Matlab, and Java with practical experience deploying deep learning for medical imaging, vision-language models, segmentation, and diffusion frameworks across neurology, ophthalmology, rheumatology, and radiology. His background spans industry (DeepRadiology, Microsoft internship) and academia (graduate researcher and TA), giving him fluency in both productionizing AI and publishing novel methods. Notably, he has focused on decentralized and efficient training approaches for healthcare models, reflecting a sustained interest in scalable, privacy-aware medical AI. Based in the San Francisco Bay Area, he brings a strong experimental mindset grounded in a PhD and MS in Computer Science from UCLA and a summa cum laude BS from Oregon State.
9 years of coding experience
4 years of employment as a software developer
Bachelor of Science (B.S.), Summa Cum Laude, Computer Science, Bachelor of Science (B.S.), Summa Cum Laude, Computer Science at Oregon State UniversityUniversity of California, Los Angeles
Github Skills (40)
python9
machine-learning9
gpu9
unet-image-segmentation9
adversarial-machine-learning9
stability8
deep-learning8
generative-adversarial-network8
pytorch7
neural-network7
numpy7
tensorflow7
gpu-acceleration6
tensor6
autograd6
Programming languages (5)
Github contributions (5)
jmerkow/R-FCN.rsna2018
Oct 2018 - Nov 2018
A Pytorch Implementation of R-FCN/CoupleNet
Contributions:123 commits in 1 month
pytorchfcnpytorch-implementation
arvindmvepa/MedTrinity-25M
Nov 2024 - Apr 2025
This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“
Contributions:250 pushes, 4 branches in 4 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.