Back home

Things I've Built

A collection of products I've shipped โ€” from App Store apps to AI-powered web platforms and internal tools.

๐Ÿณ
iOS App
Live on App Store

ChefCoach

AI-powered fridge scanning & recipe suggestions

A native iOS app that lets users scan their fridge contents and receive AI-powered recipe suggestions tailored to what they have. Built with Capacitor + Supabase backend, featuring Sign in with Apple, RevenueCat subscriptions, and a free 3-scan trial tier before paywall.

ChefCoach started from a simple problem: opening the fridge and having no idea what to cook. The app uses the phone camera to identify fridge contents, then sends the list to an AI model that returns personalized recipes. I handled the full stack โ€” iOS packaging with Capacitor, Supabase auth and database, RevenueCat for subscription management, and App Store submission.

3 free scans per day$7.99/mo ยท $59.99/yr subscriptionSign in with Apple
iOSCapacitorSupabaseRevenueCatTypeScriptXcode
โšก
Web App
Live ยท applyfy.net

Applyfy

Full-stack AI job application platform

A full-stack AI-powered job platform designed to streamline the job application process. Features intelligent job matching, application tracking, and AI-assisted cover letter generation.

Applyfy is built to make job searching less painful. The platform matches users to jobs using AI, helps them track applications in a kanban-style board, and can generate tailored cover letters. Built end-to-end with Next.js, TypeScript, Tailwind CSS, and a PostgreSQL database. Deployed at applyfy.net.

AI job matchingApplication trackerCover letter AI
Next.jsTypeScriptTailwind CSSPostgreSQLAI/LLM
๐Ÿง 
AI System
Internal ยท Production

Brain ยท AIN Ventures

LLM-powered startup pitch deck analyzer

An internal LLM system used at AIN Ventures to review startup pitch decks and apply AI-driven filtering to pre-seed investment opportunities. Handles unstructured founder data, extracts investment signals, and generates structured investment memos.

At AIN Ventures, I use Brain โ€” an internal LLM pipeline โ€” to process incoming startup pitch decks. The system extracts key signals about the founding team, market size, traction, and product differentiation, then outputs a structured memo that supports investment decisions. I also designed prompt frameworks to improve output consistency.

50+ pitch decks reviewedPre-seed deal flow filteringStructured investment memos
LLMPrompt EngineeringPythonVC AnalysisRAG
๐ŸŒ
Web App
You're Here

Portfolio Website

This site โ€” built with Next.js + TypeScript

A fully custom portfolio built with Next.js, TypeScript, and Tailwind CSS featuring animated particle systems, interactive typewriter effects, smooth scroll animations, and a warm professional aesthetic.

This portfolio was designed and built from scratch. Features a canvas-based particle animation, typewriter effect, glass-card components, and a warm periwinkle + cream color palette. Responsive across all devices.

Particle animation systemTypewriter effectsResponsive design
Next.js 16TypeScriptTailwind CSS v4React 19