Sai Polisetty
Senior Software Engineer at NVIDIA
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolSai Polisetty is a Senior Software Engineer with 7 years of experience specializing in C and Python and a strong focus on machine learning inferencing for computer vision and NLP. He has deep hands-on experience with TensorFlow, PyTorch, Keras, TensorRT, Docker, and Triton Inference Server—contributing Python backends and CI/CD integrations to Triton to enhance model serving and deployment. Sai blends ML expertise with systems-level knowledge of Linux internals, multithreading, and IPC, enabling efficient productionization of deep learning workloads. His background spans NVIDIA, Samsung R&D, and IoT startups, reflecting a mix of large-scale product engineering and embedded/voice-assistant work. Based in Bengaluru, he brings a pragmatic approach to optimizing inference pipelines and integrating cutting-edge backends like VLLM into production systems.
7 years of coding experience
7 years of employment as a software developer
Diploma, Electronics and Communication Engineering, Diploma, Electronics and Communication Engineering at Government Polytechnic College VijayawadaBachelor’s Degree, Electronics and Communications Engineering, Bachelor’s Degree, Electronics and Communications Engineering at Prasad V Potluri Siddhartha Institute of Technology
English, Telugu, Hindi
Github Skills (9)
machine-learning10
deeplearning-ai10
inference10
deep-learning10
python10
llm10
cicd9
gpu9
cloud-computing8
Programming languages (3)
Github contributions (5)
triton-inference-server/server
Oct 2023 - Apr 2025
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Role in this project:
ML Engineer
ML EngineerContributions:30 reviews, 48 PRs, 514 pushes in 1 year 6 months
Contributions summary:Sai's primary contributions involve the development and testing of Python-based backends for the Triton Inference Server. These commits include integrating a VLLM backend, adding CI/CD pipelines for these backends, and resolving code issues, highlighting a focus on the inference capabilities of the server. The code changes reveal a strong understanding of inference server architecture and integrating new backend technologies. The modifications suggest active involvement in model serving and deployment using the Triton Inference Server.
nvidia-dockernvidiadeep-learninggpuinference
pskiran1/TensorRT-support-for-Tensorflow-2-Object-Detection-Models
Aug 2021 - Sep 2023
Contributions:2 pushes, 9 comments, 1 issue in 2 years 1 month
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.