Senior Software & AI Architect | WebGPU & iOS Infrastructure | Ex-Walmart
I engineer secure, massive-scale mobile and frontend infrastructure. My technical focus lies at the intersection of enterprise iOS architecture and bleeding-edge local AI inference (WebGPU/WASM).
At Walmart, I engineered robust iOS navigation architectures (Coordinator pattern) and optimized UI rendering concurrency for millions of active monthly users. In the open-source space, I actively build privacy-first AI infrastructure, including AI that runs on the user's own device, in the browser.
- iOS: Swift, SwiftUI, UIKit, Combine, MVVM-C, Swift Concurrency, XCode
- Frontend AI: WebGPU (WASM), WebLLM, React 19, TypeScript, Manifest V3
- Backend: Node.js, PostgreSQL, Supabase Edge Functions, GraphQL, AWS
- AI & ML WebLLM, Transformers.js, MLC-LLM, Python (Pandas, NumPy)
A Privacy-First Career OS with on-device AI, in your browser.
YouxAI is not just a Chrome Extension; it's a comprehensive OS for your career.
- On-device AI: Runs Gemma 4 E2B through Google LiteRT-LM inside a local AI SDK (about 2 GB, downloaded once). There is no cloud model for filling applications.
- Résumé parsing in the browser: A deterministic parser reads the résumé on your computer. No model is involved.
- Universal Autofill: Intelligent DOM agents that navigate and fill complex application portals (Workday, Greenhouse, Lever).
Stack: React 19, TypeScript, Tailwind v4, Supabase, LiteRT-LM.
A browser-native local LLM toolkit & benchmark harness.
An open-source platform for testing, chatting with, and comparing open-weights models entirely on the client-side.
- Zero-Server Benchmarking: Runs strict parity tests (TPS, TTFT, Latency) directly on the user's hardware via WebGPU.
- Side-by-Side Comparison: Compare model outputs and latency metrics simultaneously in the browser.
Stack: Vanilla JS/HTML5, WebLLM, WebGPU, Apache TVM / WASM.
- Portfolio: ar5en1c.github.io/react-portfolio
- LinkedIn: linkedin.com/in/kuldeep-5ingh
- Email: kponia05@gmail.com