Ayush Sharma

Ayush Sharma

AI Application / Full-Stack Engineer

About

I'm an AI Systems Engineer focused on extreme optimization: getting massive AI workloads to run efficiently on constrained hardware (like a 4GB laptop GPU). My expertise is in local-first architecture, retrieval systems (RAG), and PyTorch memory management. I build the systems that make heavy neural networks run fully offline on edge devices. Most recently, I built Omnitome to demonstrate this—a desktop reading app that compresses dense text using local LLMs and custom VRAM lifecycle management. I'm driven by a long-term goal of building advanced AI systems, robotics, and frontier tech. Always learning, building, and looking for interesting problems worth solving. 🚀

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Forums

•

28m ago

Omnitome - Read 500-page books faster—with clickable source proof.

Omnitome is a local-first AI reading app that compresses dense PDFs/EPUBs ~7:1 without losing theorems or formulas. Every sentence carries a clickable citation back to the verbatim source. It runs 100% offline on a 4GB laptop GPU, processing a 500,000-word book in just 5.9 minutes with zero data egress. Built for researchers and developers who refuse to trust hallucinated AI summaries.
View more