Riddhish Bhalodia
Research Scientist at Luma AI
California, United States
Summary
👤
Senior🎓
Top SchoolRiddhish Bhalodia is a research scientist based in California with 11 years of experience building multimodal ML systems, currently focusing on post-training for large language models at Gen AI@Meta and now at Luma AI. His work spans LLMs, 3D computer vision, graphics, and clinically motivated probabilistic shape modeling from a PhD in medical image processing at the University of Utah. At Meta he drove projects from AR face tracking to codec avatars and photorealistic 3D human generation, and earlier published MICCAI work during an NVIDIA internship on cross-modal disease localization. He contributes to high-impact open-source medical imaging tooling like DIPY, improving code quality and implementing denoising and wavelet functions. Comfortable bridging research and production, he combines deep domain knowledge in healthcare imaging with practical system design for large-scale multimodal pipelines. Colleagues describe him as someone who turns complex, cross-disciplinary problems into reproducible, deployable solutions.
12 years of coding experience
10 years of employment as a software developer
Indian Institute of Technology BombayThe University of Utah
Github Skills (3)
pep10
python10
denoising10
Programming languages (6)
Github contributions (5)
dipy/dipy
Mar 2016 - Oct 2016
DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.
Role in this project:
Back-end Developer & Python Developer
Back-end Developer & Python DeveloperContributions:78 commits, 13 PRs, 97 comments in 7 months
Contributions summary:Riddhish primarily contributed to the codebase by addressing code style issues, specifically implementing PEP8 updates across various files. These updates involved formatting and restructuring code to adhere to Python's style guidelines, which enhanced code readability. The user also fixed relative imports and addressed an issue in denspeed.pyx. The user is working on the denoising and wavelet transform functions.
3dimagingmachine-learningpythonsignal-processing
riddhishb/Laproscopic-Image-Dehazing
Apr 2015 - Jul 2015
Contributions:35 commits, 21 pushes, 1 branch in 2 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.