WordScenes is a language-learning app that uses Hollywood movies and AI to teach 13 languages through immersive storytelling, with real-time translations, contextual word definitions, and personalized learning pathways. I architected the React Native app with live voice capture, Rive-powered animations, and a hybrid speech-to-text layer that dynamically switches between on-device and cloud inference. I also quantized Hugging Face Whisper models using ExecuTorch and INT8 quantization for offline pronunciation feedback, and built a Japanese NLP pipeline combining JMDict and ichiran for 50,000+ vocabulary entries.

Zebracat is an AI video platform that turns text prompts, scripts, audio, or articles into ready-to-post social videos. I led the front-end architecture for the launch with Next.js, TypeScript, and Tailwind CSS, building a scalable component system and Stripe-powered subscription flows. I also engineered PyTorch-based computer vision pipelines for scene analysis and avatar generation, integrated OpenAI and LangChain workflows into the content generation layer, and optimized the FastAPI and Redis backend video rendering pipelines.

Ashley x Descend is an online furniture auction marketplace from Ashley Canada where prices drop over time and shoppers can either place a bid or grab the item with "Buy Now". I worked on the storefront and core commerce flows (catalog, pricing, checkout, and delivery rules) with Medusa.js, Next.js, TypeScript, and shadcn/ui. I also built the auction logic that powers the live price drops and bid matching, with Node.js, Express, and PostgreSQL on the backend.

Job Wizard is an AI-powered job search Chrome extension that autofills applications across LinkedIn, Greenhouse, and Workday, plus a job tracker and ATS-optimized resume generation. I built the extension UI with React, TypeScript, and Styled-Components and engineered an intelligent form field-detection system across 100+ job portals. I also integrated a Django REST backend and introduced Jest-based testing, keeping the experience reliable across 10,000+ active installs.

Menaji is a U.S. e-commerce brand for men's skincare and cosmetics. I worked as a full-stack developer on both sides of the stack, using React, TypeScript, and Bootstrap on the front end and Node.js, Express, and MongoDB on the back end. I also integrated Shopify for product management and built a secure payment flow, with a focus on improving conversions and giving customers a more polished shopping experience.