Hi, I'm Anish 👋

I build systems at the intersection of markets, machine learning, and AI tooling — mostly quantitative trading research and reinforcement-learning sandboxes.

• 🔭 Currently working on: algorithmic options-trading research — signal detection, backtesting engines, and market-data pipelines (Alpaca / yfinance).
• 🤖 Also into: reinforcement learning and applied LLM/agent tooling.
• 🌱 Learning: better backtest methodology, execution modeling, and reward shaping for control problems.
• 💬 Ask me about: VWAP/opening-range options strategies, RL environments, or wiring Claude into research workflows.

A few things I've built

• Trading engines & scanners — VWAP-reclaim options backtesters, daily chart-triage pipelines with LLM analysis, and hybrid Alpaca data capture.
• starship-rapid-reuse-rl — an educational RL sandbox for powered-landing control (PID baseline vs. PPO).

_{📫 Reach me through GitHub.}