
I build LLM-powered products end-to-end, from the prompts and pipelines to the UI people actually click.
I'm an AI engineer, but the honest version is: I'm a builder who got obsessed with LLMs. The last couple of years I've been shipping production AI (RAG pipelines, agentic tools, and the evals nobody talks about), mostly with LangChain, LangGraph, and whatever model is winning that week (OpenAI, Gemini, Groq).
I came up doing full-stack work (Django, FastAPI, Next.js), so I tend to build AI features the way I'd build any product: as small as possible, instrumented, and within reach of a real user. Some of that ended up in CareerEdge and PandaUI; the rest lives in the side projects below.
If you're working on something interesting at the intersection of LLMs and product, I'd love to hear about it. My email's down at the bottom.
Built the rewards, referrals, store, and advertisement modules for AyeFace's merchant platform. React on top, Node.js, Firebase, and Kafka underneath.
Paste a job description, get a resume tailored to it. Built to pass ATS filters, not just look good.
A React component library for shipping marketing sites that load fast and rank well. Opinionated defaults, TypeScript-first.
A toolkit for messy text. Summarize, extract keywords, pull out entities. Originally built for marketers; now an API I keep reaching for.
A small Instagram-style image feed I built to learn Firebase real-time and Next.js together. Upload, share, like, repeat.
A chatbot that remembers context and tries to read the room. An early experiment in giving GPT a little personality.
A streetwear storefront, end-to-end: catalog, cart, Stripe checkout, admin panel. Where I learned how much an e-commerce admin actually needs.