I build AI features into products that take money.

Mula

I designed, built, and shipped a two-sided marketplace that prices work with an LLM, negotiates the gap between buyer and seller, and moves money through Stripe escrow. It runs in production today.

The problem: people describe local work badly — “my fence is falling over” — and neither side knows what it should cost, so listings stall before anyone bids. Mula resolves the request into a scoped, priced job before it is ever posted. I built every layer: frontend, backend, payments, AI, database security, infrastructure, and the LLC.

Pricing engine

Resolves an unstructured request into a scoped, priced job — LLM reasoning over live web-search rate data and vision analysis of user photos. Two layers in production.

Bid mediator

When employer and worker are apart on price, an LLM negotiates between them toward a settlement. The hardest part of the build and the reason the product exists.

Money movement

Stripe end to end — escrow held on acceptance, released on completion, paid out to connected accounts, with webhook handling and failure states.

Database security

Row-Level Security policies authored across every table in Postgres. Took the security audit from ten findings down to one.

Auth & trust

Google OAuth and magic-link sign-in, a dual-mode account model, and ID verification gating posting and bidding.

TypeScript · Next.js · React · Supabase · PostgreSQL · RLS · Stripe Connect · LLM APIs · Vision · OAuth 2.0 · Vercel

Session42

Trained and evaluated AI music generation models on an ML research team — built and curated the training datasets, and wrote the structured output-quality assessments that fed back into the models. Ten years producing music is what made me useful there: evaluating a generative audio model is a listening problem before it is a metrics problem. I could hear what the model got wrong and write down why in terms the engineers could act on.

Work

• AI features built into an existing product
• Agent and tool-use workflows
• RAG and retrieval systems
• Stripe, escrow, and payouts
• Next.js / Supabase full-stack
• Model evaluation and dataset curation