Tejaswi Kasarla is a PhD candidate in the VIS Lab at the University of Amsterdam and an ELLIS-funded researcher specializing in computer vision and autonomous driving perception. With a decade of experience across academia and industry, he has worked on 3D object detection, tracking, large-scale ego-vehicle event detection, and knowledge distillation for semantic segmentation at Bosch and during research roles at IIIT-H and Meta. His work blends rigorous research—evidenced by visiting researcher exchanges in Europe and an industry research internship at Meta—with practical system-building for embedded and real-world applications such as pediatric visual field devices. Comfortable moving between theory and production constraints, he often tackles data- and compute-limited settings to make models more efficient and deployable. Based in Amsterdam, he brings an international perspective and a track record of translating academic ideas into industry-impacting prototypes.
10 years of coding experience
5 years of employment as a software developer
Bachelor of Technology (B.Tech.) Electrical and Electronics Engineering, Bachelor of Technology (B.Tech.) Electrical and Electronics Engineering at Mahatma Gandhi Institute of Technology
MS by Research Computer Science, MS by Research Computer Science at International Institute of Information Technology Hyderabad (IIITH)
Doctor of Philosophy - PhD Artificial Intelligence, Doctor of Philosophy - PhD Artificial Intelligence at University of Amsterdam
Github code for the paper Maximum Class Separation as Inductive Bias in One Matrix. Arxiv link: https://arxiv.org/abs/2206.08704
Contributions:23 commits, 1 PR, 21 pushes in 4 months
pytorchmaximumarxivabsinductive-biases
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.