Balarama Buddharaju
Senior Software Engineer at NVIDIA
Pittsburgh, Pennsylvania, United States
Summary
🤩
Rockstar🎓
Top SchoolBalarama Buddharaju is a Senior Software Engineer in Pittsburgh focused on applying machine learning to computer vision and robotics, with two years of professional experience currently working on TensorRT for deep learning inference at NVIDIA. He previously built learning-based motion forecasting and prediction systems for autonomous vehicles at Motional and developed lidar perception and multi-sensor fusion pipelines at Cyngn. His background blends academic research—teaching deep reinforcement learning at CMU and working on vision-in-the-loop bipedal robot control—with hands-on production engineering for safety-critical systems. Trained in computational design and manufacturing (CMU) and mechanical engineering (BITS Pilani), he brings a rare mix of control, perception, and systems expertise that helps bridge research and real-world autonomous platforms.
2 years of coding experience
9 years of employment as a software developer
BITS Pilani, Birla Institute of Technology and ScienceMaster's degree Computational Design & Manufacturing, Master's degree Computational Design & Manufacturing at Carnegie Mellon University
Github Skills (16)
tensorrt10
latency10
throughput10
nvidia10
optimizer10
inference10
sdk10
low-latency10
backend9
high-performance9
gpu-acceleration9
machine-learning9
deep-learning9
nvidia-docker9
tensorflow8
Programming languages (1)
Github contributions (4)
brb-nv/TensorRT-LLM
Mar 2025 - Apr 2025
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Contributions:42 pushes, 7 branches in 9 days
NVIDIA/TensorRT-LLM
Mar 2025 - Apr 2025
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Contributions:17 reviews, 5 PRs, 32 comments in 10 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.