Harshith Kumar
Imaging Software Engineer at GLASS Imaging
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHarshith Kumar is an imaging software engineer and computer vision researcher with 6 years of experience building robust perception systems for autonomous vehicles and edge deployment. His MS work at UC Riverside introduced self-supervised thermal–RGB optical flow for night-time AV perception, complementing hands-on industry impact at Intel where he reduced collision-alert false positives by 30% and automated object-labeling with a semi-supervised PyTorch framework that improved model accuracy by 20%. Now at GLASS Imaging in San Francisco, he focuses on bridging deep learning with hardware through CUDA optimization and multimodal sensor fusion. He’s published at top venues (CVPR/ICCV), taught the self-driving stack using CARLA, and contributes to prominent open-source documentation like TensorFlow’s tutorials, showing both research rigor and practical engineering discipline. Notably, he has experience scaling multimodal pipelines on large HPC GPU clusters and a penchant for making complex tooling accessible to learners and production teams.
6 years of coding experience
2 years of employment as a software developer
Bachelor of Technology - BTech, Computer Science, Bachelor of Technology - BTech, Computer Science at PES UniversityMechanical Engineering, Mechanical Engineering at De Anza CollegeMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of California, RiversideMonta Vista High School
English, Telugu, Kannada
Github Skills (8)
keras10
jupyter-notebook10
tensorflow10
documentation10
machine-learning9
deep-learning8
deeplearning-ai8
python7
Programming languages (3)
Github contributions (5)
tensorflow/docs
Oct 2020 - Oct 2020
TensorFlow documentation
Role in this project:
Technical Writer
Technical WriterContributions:5 commits, 1 PR in 1 day
Contributions summary:Harshith's commits primarily involve modifications to a Jupyter Notebook file related to a Keras text classification tutorial. The changes include copyright and license information, and the removal of notebook outputs. This suggests a focus on preparing and refining the documentation and example code within the tutorial for the TensorFlow documentation project. The commits aim to maintain the integrity and clarity of the tutorial.
deep-learningmachine-learningdeep-neural-networkstensorflow-tutorialstensorflow
Harsh188/100_Days_of_ML
Sep 2020 - Dec 2020
Contributions:243 commits, 100 pushes, 1 branch in 3 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.