// ABOUT

Jordan Bee

Quant systems engineer building autonomous algorithmic trading systems from scratch. I combine AI/ML, distributed infrastructure, and disciplined risk management to trade crypto perpetuals on Hyperliquid with real capital. Everything you see on this site is running live.

Skills

Full-stack from signal generation to production execution.

// AI & ML
  • LLM orchestration and routing
  • Multi-agent systems (8 specialized agents)
  • Signal generation and regime detection
  • Prompt engineering and chain design
// QUANT TRADING
  • Kelly criterion and fractional sizing
  • Mean reversion and momentum strategies
  • Backtesting with walk-forward analysis
  • Information coefficient and signal evaluation
// INFRASTRUCTURE
  • Multi-VPS distributed architecture
  • Docker, systemd, deployment automation
  • Real-time WebSocket data pipelines
  • Monitoring, alerting, and auto-recovery
// BACKEND
  • Python (trading engine, risk systems)
  • Elixir/OTP (Pulse real-time service)
  • REST and WebSocket API design
  • SQLite, PostgreSQL, shared state
// FRONTEND
  • SvelteKit with SSR and edge deployment
  • Three.js, GSAP, WebGL visualizations
  • Tailwind CSS, responsive design
  • Real-time data dashboards
// DEVOPS
  • TDD with 1000+ unit tests
  • CI/CD and automated deployment
  • Git worktrees, code review workflows
  • Security auditing and pen testing

Why I Trade Algorithmically

Discretionary trading is a losing game for most people. Not because the market is rigged, but because human psychology is fundamentally misaligned with what makes money. We cut winners short and let losers run. We overtrade after wins and freeze after losses. We see patterns in noise.

Algorithmic trading removes the human from the loop. The system does not feel fear after a drawdown. It does not get greedy after a streak. It executes the same strategy at 3 AM on a Sunday as it does at market open on a Monday. The edge is consistency.

A 49% win rate sounds terrible until you realize the TP:SL ratio is 1.8:1. The math works out to positive expected value on every trade. But only if you actually take every trade, with the correct sizing, without flinching. A human cannot do that reliably. A machine can.

That is why I build systems instead of trading manually. The code is the discipline. The backtest is the evidence. The live P&L is the proof.