Kumara Kahatapitiya
Research Scientist at Meta
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolKumara Kahatapitiya is a Research Scientist at Meta GenAI with nine years of experience bridging academic research and industry R&D in computer vision and machine learning. He completed a PhD at Stony Brook University focused on efficient representations for video understanding and generation, and has interned or collaborated with DeepMind, Qualcomm AI Research, and Meta, bringing research ideas toward practical, scalable models. His background spans end-to-end CV/ML work from his B.S. in Electronic & Telecommunication Engineering at University of Moratuwa to graduate research roles, evidencing strong systems and modeling expertise. Kumara’s trajectory shows a consistent focus on video-centric problems, but also a knack for translating theory into applied research during industry internships. Based in New York, he blends deep technical rigor with cross-organizational experience, making him adept at tackling challenging generative and representation learning problems. An understated strength is his steady progression through diverse research environments, suggesting both adaptability and sustained impact across academia and industry.
9 years of coding experience
7 years of employment as a software developer
B.S. in Engineering (Hons), Electronic & Telecommunication Engineering, B.S. in Engineering (Hons), Electronic & Telecommunication Engineering at University of MoratuwaPhysical Science stream, Physical Science stream at Nalanda College ColomboDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Stony Brook University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (23)
compression10
x3d9
pytorch9
machine-learning9
inference9
mixture-of-experts9
tensorflow9
gpu9
data-parallelism9
deepspeed9
deep-learning9
visual-question-answering8
distributed-training8
diffusion-models5
caching5
Programming languages (3)
Github contributions (5)
kkahatapitiya/Occlusion-Removal
May 2019 - Feb 2020
Contributions:11 commits, 2 pushes in 9 months
kkahatapitiya/Coarse-Fine-Networks
Mar 2021 - Oct 2021
Code for our CVPR 2021 paper "Coarse-Fine Networks for Temporal Activity Detection in Videos"
Contributions:18 commits, 11 pushes, 1 branch in 7 months
activity-detectionefficient-video-architecturespytorch
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.