Jitendra Kolhe
Senior System Software Engineer at NVIDIA
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolJitendra Kolhe is a Senior System Software Engineer with 12+ years of hands-on experience in operating systems, hypervisors and accelerator software, currently working at NVIDIA after leading system and compiler work for AI accelerators at HPE. He has deep kernel and virtualization expertise—having improved QEMU start-up times by ~25x, expanded HPVM to 32 vCPUs and enabled live vCPU add/remove and migration for HP-UX guests. Jitendra also redesigned HP-UX virtual memory init to cut boot time by over 75% and built compiler backends, loaders and emulators for a neural-network Dot Product Engine. Early in his career he developed mobile games and cross-platform engines, giving him a rare blend of low-level systems, compiler and applied software engineering. Based in Bengaluru, he combines pragmatic performance optimization with architecture-level design for compute and virtualization platforms.
12 years of coding experience
4 years of employment as a software developer
B.E., Computer Science, B.E., Computer Science at Mumbai University - R.A.I.T
Github Skills (18)
video-understanding10
language-model8
computer-vision8
tegra8
retrieval-augmented-generation8
nvidia8
generative-ai7
ai6
gpu6
linux-kernel6
caf3
upstream3
deepstream2
nexus1
atmel1
Programming languages (3)
Github contributions (5)
NVIDIA-AI-Blueprints/video-search-and-summarization
Apr 2025 - Jul 2025
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
Contributions:1 release, 1 push, 3 tags in 2 months
aigpulanguage-modelnvidiarag
NVIDIA-AI-IOT/DeepStream_Coding_Agent
May 2026 - May 2026
A project showcasing how to leverage AI coding assistants (Cursor, Claude Code, etc.) for accelerated NVIDIA DeepStream SDK application development using a curated agentic skill and structured prompts.
Contributions:1 push in 1 day
agenticaiclaudedeepstreamnvidia
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.