Akshay Paruchuri
Visiting Faculty Researcher at Google
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolAkshay Paruchuri is a postdoctoral scholar and visiting faculty researcher blending nine years of experience across health AI, computer vision, and embedded systems with a current focus on multimodal agents and interpretability at Stanford and Google. He has driven research to make AR smart glasses practical for all-day use and advanced context-aware, multimodal assistants for health and well-being. His work spans academia and industry, from a PhD at UNC Chapel Hill to internships and research stints at Google, Kitware, and IDSIA, reflecting a strong cross-disciplinary skillset. An active ML engineer contributor, he improved training pipelines and schedulers in the NeurIPS 2023 rPPG-Toolbox for remote PPG, highlighting practical impact on physiological sensing models. Comfortable shipping both firmware for connected fitness at Nike and state-of-the-art ML research, he bridges hardware constraints and deep learning rigor. Known for combining rigorous experimentation with production-minded engineering, he operates at the intersection of perception, language, and health-focused AI.
9 years of coding experience
6 years of employment as a software developer
Bachelor of Science - BS, Electrical and Computer Engineering, Bachelor of Science - BS, Electrical and Computer Engineering at North Carolina State UniversityDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at The University of North Carolina at Chapel Hill
English, Telugu, Urdu
Github Skills (7)
computer-vision10
pytorch10
machine-learning10
deep-learning10
python10
configuration-management9
configuration-manager9
Programming languages (4)
Github contributions (5)
ubicomplab/rPPG-Toolbox
Jan 2023 - Jan 2023
rPPG-Toolbox: Deep Remote PPG Toolbox (NeurIPS 2023)
Role in this project:
ML Engineer
ML EngineerContributions:64 reviews, 6 commits, 58 PRs in 13 days
Contributions summary:Akshay's commits primarily focused on implementing and modifying training routines for various deep learning models within the rPPG-Toolbox. They introduced and adapted learning rate schedulers (StepLR, OneCycleLR), updated trainer classes to utilize these schedulers, and incorporated a configuration option to use the last epoch for testing. Furthermore, they updated model training and validation processes within the repository, modifying the configuration options and incorporating data validation steps. The changes span multiple training scripts, highlighting a focus on improving the training pipeline and model evaluation.
cameracardiovacomputer-visiondeep-learninghealth
yahskapar/rPPG-Toolbox
Oct 2022 - Mar 2025
Contributions:148 pushes, 50 branches in 2 years 5 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.