Divakar Verma
Sr. Software Engineer - VLLM at AMD
Austin, Texas, United States
Summary
👤
Senior🎓
Top SchoolDivakar Verma is a senior software engineer with 11 years of experience specializing in optimizing AI model inference for GPUs, currently focusing on vLLM and ROCm performance at AMD. His background spans deep learning systems at NVIDIA, production ML for voice and camera at Flipkart and Samsung, and research-grade modeling and HPC work from stints at University of Melbourne and Rutgers/Princeton studies. He has a proven track record shipping latency- and resource-sensitive ML features for mobile and server deployments, including commercialized image and video enhancements on flagship smartphones and ASR/Text-to-Speech pipelines. Comfortable bridging research and production, Divakar combines low-level performance tuning with model-level expertise—an asset for teams pushing large-model inference into real-world constraints.
10 years of coding experience
3 years of employment as a software developer
BITS Pilani, Birla Institute of Technology and ScienceMaster of Science - MS Computer Science, Master of Science - MS Computer Science at Rutgers University–New BrunswickComputer Vision, Computer Vision at Princeton University
English, Hindi
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (12)
github-pages10
jekyll10
responsive10
jekyll-theme10
javascript9
open-source9
merge6
image5
css4
patch4
react3
moveit3
Programming languages (3)
Github contributions (5)
vdivakar/Papers-Stack
Jun 2021 - Sep 2021
Contributions:19 commits, 18 pushes, 1 branch in 2 months
vdivakar/Testing-static
Apr 2020 - May 2020
Contributions:2 PRs, 227 pushes, 3 branches in 14 days
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.