Keval Morabia

Staff Deep Learning Engineer at NVIDIA

Ahmedabad, Gujarat, India
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Keval Morabia is a Staff Deep Learning Engineer at NVIDIA with eight years of experience building and optimizing production-ready AI systems, having joined NVIDIA through the OmniML acquisition where he was a founding team member. He specializes in quantization, pruning, and knowledge distillation for LLMs and maintains the TensorRT Model Optimizer toolkit to deliver hardware-efficient model deployments across NVIDIA and edge devices. His background spans research and production roles at Bloomberg, Microsoft Research, and AWS, where he built self-service model maintenance pipelines, document tagging systems, and scalable training/deployment infrastructure. A UIUC MS and BITS Pilani alum, he combines deep research rigor with hands-on engineering and is also an avid travel content creator who applies the same meticulous planning to both model optimization and multi-city itineraries.
code9 years of coding experience
job7 years of employment as a software developer
bookBITS Pilani, Birla Institute of Technology and Science
bookUniversity of Illinois Urbana-Champaign
languagesEnglish, Hindi, Gujarati
github-logo-circle

Github Skills (147)

transformers10
webpage-screenshot10
language-model10
python10
diffusion-models10
text-to-speech10
automatic-speech-recognition10
transformer-models10
deep-learning10
image-generation10
self-attention10
speech10
gpu10
quantization10
gpu-acceleration10

Programming languages (9)

TypeScriptJavaC++CRustTeXSassHTML

Github contributions (5)

github-logo-circle
This project contains the implementation of basic graph theory algorithms like BFS, DFS, Kruskal's MST, Prim's MST, Dijkstras Shortest Path
Contributions:3 commits, 1 push, 1 branch in 8 months
graph-theorydfsbfsdisjoint-setdijkstra-shortest-path
This is an implementation of Apriori algorithm for frequent itemset generation and association rule generation. The GUI is made using JAVA FX or Cmd_Line version can be used
Contributions:69 commits, 32 pushes, 1 branch in 1 year 4 months
apriorijavafxjavadata-miningassociation-rules
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.
Request Free Trial