Los Angeles
AI Engineer building reliable AI-native products from 0 to 1.
I ship LLM products end to end: tool-calling agents, real-time voice AI, and the eval suites that keep them working in production.
I also run build sessions and make websites for local businesses. Two ways to work with me.
My NBA dreams didn't pan out, so I redirected the obsession into software.
NBA Finals Prediction: 76ers vs Lakers · 7/26/26

I help people become AI enabled. One hour at a time, on a screen share, until you can build things yourself. And if you don't have the time for that, I'll just build it for you.
A selection
Social media isn't social. People scroll for hours and end up lonelier than when they started.
A social web app with an AI agent that plans real-world meetups from natural-language chat. Built on a Claude tool-calling agent with multi-turn confirmation and safety guardrails, a real-time voice AI moderator (Pegasus, on LiveKit), and ~20 generative endpoints. Backed by a unit-test suite that encodes past agent failures as regression tests.
Shipped the MVP. Co-founded and built 2025–2026.
People want spiritual guidance but don't know where to start or how to apply ancient wisdom to modern life.
An iOS app giving personalized, scripture-grounded spiritual guidance. A persona-constrained LLM assistant (Claude) with a scripture-sourced system prompt and citation rules, backed by structured verse and commentary data.
Grew to 200+ users at peak
Basketball stats are scattered and hard to read. Coaches, scouts, and fans want clear insights without digging through raw box scores.
A web app that turns player and team stats into visual, digestible analysis for coaches, scouts, and super-fans.
Live web app
I take LLM products from idea to production: tool-calling agents, RAG, structured outputs, and real-time voice AI. Hands-on with Claude and OpenAI APIs, the Vercel AI SDK, and LiveKit.
Next.js, React, React Native, TypeScript, Python. Supabase, Firebase, Vercel. From idea to a live, monetized app.
The reason my AI features hold up in production. Eval suites and regression tests turn every agent failure into a named test, so the same bug can't ship twice. Six years of quality engineering, pointed at non-deterministic systems.
Infosys
Prathibha Management
CSU Fullerton, 2025
4.0 GPA
UC Riverside
A Claude tool-calling agent, a voice AI moderator, and the test suite that keeps them from breaking.
AI removes friction, and friction is what builds cognition. Don't outsource your mind.
Want to talk AI products or basketball? Either works.