Systematic Trader · AI Systems Builder
Building transparent, versioned crypto execution systems with regime logic, circuit breakers, and strict guardrails—for measurable edge and disciplined psychology.
Thessaloniki, Greece · X: @srdevb
- Versioned BTC execution systems with frozen rules and checkpointed upgrades
- MAE/MFE integrity tracking, expectancy monitoring, and regime-aware diagnostics
- Linux automation stack: scripts → tmux workflows → watchdogs → safe execution
- Stability under pressure: freeze windows and post-trade review protocols
A disciplined execution engine built for transparency and control:
- Signal with confirmation + regime detection (volatility/trend context)
- Pre-entry rejection filters for weak or uncertain regimes
- Live MAE/MFE watchdogs and circuit breakers
- Scaling ladder with monitored checkpoints
- No mid-cycle optimization (changes only at checkpoints)
Design intent: measurable, explainable, and safe to run under real pressure.
|
Estimation, control, and planning fundamentals. Foundation for disciplined engineering. |
Research exercises and early explorations in feature engineering and ML-driven signals. |
|
PyTorch implementations of RL algorithms used to build intuition for dynamic decision systems. |
CLI tool for tracking review queue positions with clean, stable utility code. |
Python pandas NumPy PyTorch scikit-learn Jupyter
Linux Docker tmux VS Code Cursor
TradingView Pine Script CCXT Coinbase Perps
- Risk first: sizing, SL/TP asymmetry, circuit breakers
- Frozen rules: change only at checkpoints with enough data
- Track edge: expectancy, MAE/MFE, volatility context
- Keep systems simple; losses are data
- LLM-assisted journaling, diagnostics, and signal triage
- Automated post-trade evaluation with regime tagging and edge tracking
- Meta-system design: versioning, freeze windows, scaling ladders, stability as margin scales
Where disciplined execution meets emotional resilience.
If you want to build something measurable and real, reach out.