
Surface | Cross-Exchange Arbitrage
2026Cross-exchange prediction market arbitrage scanner. Finds pricing edges between Kalshi and Polymarket using semantic matching.
Software engineer and data scientist with a focus on finding edges in inefficient systems.
Currently building surface.surf, a cross-exchange prediction market aggregator.

Cross-exchange prediction market arbitrage scanner. Finds pricing edges between Kalshi and Polymarket using semantic matching.

Prediction market backtesting and live trading system. Replicates real market conditions with clock abstraction and order simulation.

Job search aggregator with semantic resume matching. Scrapes LinkedIn and uses embeddings to rank jobs by relevance.
MLB player props prediction system with probability distributions. Monte Carlo backtesting on PrizePicks and similar platforms.
Started programming at 16 building Supreme bots. They mostly didn't work, but I learned reverse engineering, browser automation, and how to find edges in systems. Did $16k volume on StockX.
During COVID, shipped spoti-cli, a terminal Spotify client with vim bindings.
Got into Solana NFTs in 2021, built DAO tools, and exited before the crash.
Spent 2023-2025 deep in baseball modeling. Built a full prediction system for MLB player props with ridge regression, rolling stats, and Monte Carlo backtesting. Never placed actual bets, but the system works end-to-end.
Graduated from Berkeley with a Data Science degree in December 2025. The poker course unexpectedly connected to prediction market work.
Python (ML/ETL), Go (systems/APIs), TypeScript (frontend), SQL
pandas, scikit-learn, XGBoost, dbt, PostgreSQL, pgvector
FastAPI, Go chi, SQLite/Turso, Redis for caching
React, Next.js, Tailwind, Streamlit, Bubbletea TUI
Docker, Vercel, Railway, GitHub Actions CI/CD
Prediction markets, sports analytics, reverse engineering, TUIs