Systematic 0DTE Options Trading
Defined-risk options strategies on SPX and index products, driven by dealer positioning and regime. These systems carry strong Calmar and Sortino ratios across forward testing and live management.
Algorithmic Trading · Real-Time Financial-AI Systems
Real-Time Market-Structure Intelligence
Real-time 0DTE SPX options-microstructure infrastructure, with a self-hosted AI layer that reasons over live market structure.
Some methodologies
Focus areas
Real-Time Market Microstructure
Tick-level ingestion and per-minute aggregation of gamma / delta / vega exposure, charm, skew, max-pain and net-premium drift across the full 0DTE SPX chain, VIX and 250+ concurrent instruments.
Applied AI for Trading
Local LLM agents that learn the way I trade — from my notes, daily write-ups and past sessions — through a pgvector memory layer, pre-warmed with dense structural summaries instead of raw ticks.
Quantitative Research & Backtesting
A strategy registry with walk-forward validation and prop-firm drawdown/survival modeling, with reproducible result caching for honest, comparable evaluation.
What I'm currently building
Self-hosted inference for real-time trading
Today I rotate one-shot calls across commercial APIs — Claude (the most capable), plus Gemini, Mistral and others — feeding each a tightly compressed market summary, because tick-level data won't fit and the plan caps run out mid-week. Moving to a self-hosted model removes the cap and lets me benchmark what actually matters for trading:
Latency
Time-to-first-token and generation latency low enough to fit inside scalping execution windows.
Requests per minute
Sustained, minute-by-minute context injection through the session without thermal or VRAM bottlenecks.
Data throughput
Rapidly experimenting to learn which real-time signals carry edge — and which are noise — across high volumes of structured market data.
Execution integration
Decision speed fast enough for the model to react inside scalping windows — quicker than manual execution of the same methodology.
The longer-term goal is a refined local model with durable long-term memory — warmed from summary profiles and continuously taught my methodology — running at high throughput on dedicated hardware.
Selected work
Systems I've built
KGB-ONE Options Intelligence
A real-time SPX options analytics and automated-reporting platform: per-minute dealer-exposure snapshots, filtered net-premium drift, regime detection, and gated end-of-day / pre-open / intraday report generation — surfaced through a React charting portal, with verification gates on every published figure.
Local AI Agent Stack
Multi-agent orchestration over a knowledge base of thousands of embedded research chunks with structured tool use. It learns from my daily write-ups and past sessions via pgvector — and is being moved off API caps onto self-hosted hardware at near-zero marginal cost per token.
Research & Backtest Engine
Backtesting, a strategy registry and signal research (dealer-positioning, regime and ML families) with prop-firm survival simulation and reproducible, cached result sets for comparable evaluation.
PKI, WebTrust & Cryptography
Earlier career · 2001–2015
Two generations of WebTrust-certified public-key infrastructure — multi-layer CAs, registration authorities, LDAP, and OCSP — deployed to government, banking, and industrial clients across 30+ countries. HSM-integrated custom cryptography, smart-card platforms, and a granted patent for digital authentication of valuable goods. Secure data centres built to WebTrust and DoD Level 5 specifications; annual WebTrust audit programmes; EU EEMA PKI interoperability standards work.
Digital identity, social networks & blockchain
Earlier career · 2001–2015
Secure credential and password-management platforms across web, desktop, and mobile — X.509 digital IDs, encrypted local stores, and biometric integration. Consumer social-network systems for major sports franchises with Facebook/Twitter APIs, content management, and fan push alerts. Smart-card authentication architectures; commercial certificate and subscription transaction portals. Cryptocurrency and blockchain identity infrastructure for digital-asset provenance and secure transactions.
Daily intelligence
End-of-day reports
Every session my stack generates an end-of-day market report — dealer-positioning, regime, flow and the levels that matter — fronted by $RAVOLM, a regime-aware animated volume visualisation. A few recent ones:
2026-08-21 · Friday
The magnet and the accelerant are the same strike
SPX +0.43% to 7,674.37 | a 37pt range that stalled 3pt short of 7,700, into a Monday book short gamma on both flanks
2026-08-20 · Thursday
The gamma window shut at 11:06 and the near-spot book never turned again
SPX -0.87% to 7,641.16 | one positive-gamma half-hour, the high inside it, then a close on the low
2026-08-19 · Wednesday
The book that built in a day came off in a day
SPX gapped 25pt on the Treasury buyback announcement, ran to 7,743.93 at 11:01, then faded five hours to close 7,707.98. Underneath, the near-spot short-delta book unwound 86% in a single session, back to where it stood before Tuesday's build
2026-08-18 · Tuesday
Forty-five points before the bell, twenty-five after it
SPX opened 45pt under Monday - more than the whole move priced for the day - then went nowhere, holding a 25pt range into a 7,688.63 low and closing 7,691.76. The cash session gave 8 of the day's 53 points
2026-08-17 · Monday
The open was the high and the close was the low
SPX printed 7,790.68 in the opening minute and never saw it again, then held a five-point box while the near-spot gamma book flipped sign eleven times. At 12:41 it stopped flipping and stayed negative - price bled to 7,744.88 and closed at 7,745.06, on its low
2026-08-14 · Friday
Thirty-four points, all of them spent going nowhere
SPX made its high 35 minutes in at 7,810.01 and spent the next six hours giving it back, bottoming at 7,776.31 at 1:37pm before basing there and closing at 7,785.76. A 33.7-point range against an expected 25.6 - the day used its move without going anywhere
2026-08-13 · Thursday
The open was the low, and 7,800 pulled all day
SPX gapped into 7,763.18, never traded a tick below it, and spent 90% of the session above the expected-move top the prior book had put at 7,781. It closed at 7,798.99
2026-08-12 · Wednesday
Three Quarters of the Gap Came Back, Then the Book Rebuilt Underneath It
SPX gapped 37.3 points to a 7,766.01 opening high, gave back 27.5 into a 10:31 low that held above Tuesday's close, then ground back on a near-spot book inflating to +508.3 $M/$1 by 14:46, closing 7,748.50 (+0.26%)
2026-08-11 · Tuesday
The High Was the Opening Print
SPX gapped to a 7,767.51 open that was the session high, then bled all day to a 7,717.25 low at 14:29 as near-spot gamma and delta both crossed negative by 12:41 — a regime change, not an exhaustion low — closing 7,728.20 (−0.32%)
2026-08-10 · Monday
Thirty Points, and the Day Stopped a Point Short of the Call Wall
SPX never traded 17 points either side of its 7,751.74 open — the 10:49 high stopped 1.24 under the 7,775 call wall without tagging it, and the 12:44 low came as near-spot gamma troughed at −$92.1M, closing 7,753.11 (−0.06%)
2026-08-07 · Friday
The Long-Delta Anchor Walked 145 Points Up the Ladder
SPX gapped 25.2 points above Thursday and never traded back, running to 7,763.08 at 11:33 then fading to 7,734.39 at 14:46, where gamma flickered negative for one minute and re-inflated, closing 7,757.64 (+0.62%)
2026-08-06 · Thursday
The High Came Early and Nothing Came Back For It
SPX took its whole upside to a 7,742.85 high by 10:20 and spent 76% of the day beneath the prior close — the 7,700 strike flipped from +$610M of delta to −$483M around 11:15 — basing after a 7,698.15 low to close 7,709.96 (−0.18%)
2026-08-05 · Wednesday
Gap-and-Fade: High of Day in the First Minute
SPX opened 7,786.97 on a +50-point gap, printed its 7,793.68 high at 09:31 and never looked back up, selling to a 7,720.17 low as near-spot positive delta drained from +$13.1B to +$1.4B, closing 7,723.55 (−0.17%)
2026-08-04 · Tuesday
A 136-Point Grind, Then The Bell Took 22 Back
SPX gapped up 30 points, printed a low inside eight minutes and never traded back through it, grinding 129 points higher as near-spot positive delta built to +$49.8B; a $4,479M sell MOC took it off the 7,758.21 high to close 7,736.52 (+1.79%)
2026-07-31 · Friday
Down 38 Points Below Thursday, Then A Six-Hour Climb To The High
SPX gapped up 24 points and handed it all back inside forty minutes, flushing to a 7,399.83 low with the near-spot book at its most destabilised; the speed of the repair by 10:40 turned it, and six hours of grind closed 7,489.72
$RAVOLM (Regime-Aware Animated VOLM) — research/visualisation, not financial advice.
Curriculum vitae
Profile
CISO and CTO background with 20+ years in regulated financial services and digital security — alongside full-stack systems development at the intersection of quantitative trading and applied AI. Designs, builds and operates systems such as real-time 0DTE SPX options analytics, dealer-exposure and regime engines, and a multi-agent AI / reporting layer with pgvector memory. These trading systems carry strong Calmar and Sortino ratios across forward testing and live management — with work now underway toward self-hosted LLM inference to apply local models to trading methodology at high throughput.
Core competencies
- Systematic options trading — defined-risk SPX / 0DTE strategies; risk-adjusted performance (Calmar, Sortino) across forward testing and live management
- Real-time market-data engineering — DXLink / WebSocket ingestion, TimescaleDB hypertables, Redis Streams event bus, Dockerised microservices on Linux with systemd
- Options analytics — GEX / DEX / VEX, charm, dealer positioning, max-pain, skew & term structure
- Quantitative research & ML — Backtrader walk-forward validation, prop-firm survival modeling, scikit-learn / XGBoost signal work; Parquet-derived cache layers for bulk pandas replay (Postgres as source of truth, columnar extracts where SQL would be the wrong tool)
- Live trading integration — broker and execution APIs across Tastytrade, Schwab (thinkorswim), MooMoo (Futu OpenD API), and cTrader (prop-firm FIX / Open API + Protobuf); DXLink market-data feeds
- Full-stack web engineering — FastAPI backends, React + Vite + Tailwind front ends, Plotly interactive charting and research portals
- Applied AI & agent systems — multi-agent orchestration, RAG over pgvector and Neo4j, tiered LLM dispatch with rate-limit metering, structured tool use, self-hosted inference (vLLM / Ollama)