Akul Gupta
Software Engineer at Meta
San Jose, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAkul Gupta is a software engineer based in San Jose with a strong focus on computer vision, VIO-SLAM, and real-time AR/VR systems. In roles at Meta Reality Labs, Niantic, and 8th Wall he shipped C++ and full-stack solutions that bridge low-latency sensor fusion, mapping, and multiplayer AR—reducing scale error by up to 40% and enabling sub-20ms cloud-mesh depth decoding. His background blends ML research (RNNs and neuroscience-inspired detection) with practical systems work in WebGL, WebAssembly, and React, giving him fluency across embedded, GPU, and web runtimes. Though early in his career, he’s repeatedly delivered production-facing SLAM improvements and tools that make maps more interpretable for downstream applications. He brings an uncommon mix of academic curiosity about brain-inspired algorithms and hands-on engineering for latency-sensitive AR/XR products.
1 year of coding experience
3 years of employment as a software developer
University of California Santa Cruz
Stackoverflow
21reputation
1kreached
0answers
1question
Github Skills (15)
nvidia10
runtimes10
pytorch9
python9
large-language-models9
cpp9
tensorrt9
cuda9
inference8
llm8
php6
cakephp6
phinx6
mysql6
migration6
Programming languages (1)
Github contributions (1)
NVIDIA/TensorRT-LLM
Jan 2025 - Feb 2025
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Contributions:3 releases, 3 reviews in 6 days
cppinferencelarge-language-modelsllmnvidia
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.