JD

Work

What I've Built

Production systems first, experiments second. Every claim here is one I can walk you through.

In Production at AirSprint — built solo

Production

Jetty — Internal AI Agent Platform

AirSprint's internal AI agent platform, built so ~400 employees get AI over company knowledge with zero per-seat licensing cost. One agent with a governed tool belt and contextual query rewriting: document RAG with hybrid retrieval (pgvector + Postgres full-text search, RRF fusion, Cohere rerank), text-to-SQL tools over the data warehouse, an email-gated read-only Salesforce SOQL tool, and an employee directory — a single Python Lambda brain (Docker) on AWS Bedrock, fed by a SharePoint → S3 → pgvector ingestion pipeline. The architecture evolved from a router + specialist agents to a single agent with tools as tool-selection reliability improved, and it's validated by a golden-question regression suite plus stress tests.

~400 employees served $0 per-seat cost One agent · 4 tool domains Golden-set regression evals
Python AWS Lambda AWS Bedrock pgvector RAG Cohere rerank text-to-SQL Agents
Internal production system — ask me about the architecture
Production

AirSprint Data Platform

The company data warehouse, designed and stood up from nothing — a medallion-architecture (Bronze/Silver/Gold) platform on PostgreSQL/RDS consolidating Salesforce, FL3XX flight-ops, and HelpScout, built to retire a fragile Snowflake/dbt pipeline. All infrastructure self-provisioned: in-VPC EC2 ingestion server, S3 data lake, private networking, key-less IAM security (zero static credentials), a cross-compile → S3 → SSM deploy pipeline, and failure alerting. A generic Go CDC pipeline does 15-minute incremental upserts, replacing ~5 legacy full-snapshot jobs with one mechanism. Key metrics reconciled exactly to legacy numbers before cutover.

~472K records · 22 objects ~142K flight legs 5 legacy jobs → 1 CDC pipeline Zero static credentials
Go PostgreSQL / RDS S3 EC2 / SSM CDC / ELT Salesforce FL3XX systemd
Internal production system — ask me about the architecture
Production

FlightDeck + API Server

AirSprint's internal operations platform — I'm its sole developer (Go backend + Next.js frontend) — and the OpenAPI-driven Go API server it runs on — the single data path between apps and the warehouse, decoupling serving from ingestion. Shipped features include passport MRZ scanning with eAPIS XML conversion (AWS Textract), an employee empty-leg booking perk, a per-diem/empty-leg payroll engine, bitmask route-level RBAC including a ~1,600-user owner-portal roster, and fleet-utilization and crewing dashboards. Absorbed an external Salesforce contractor's work — replicating Salesforce workflows in-app to sharply cut license spend — with a strangler rewrite of the contractor-built client booking application underway.

Contractor work absorbed ~1,600-user RBAC roster MRZ / eAPIS scanning Single app data path
Go Next.js OpenAPI AWS Textract PostgreSQL RBAC
Internal production system — ask me about the architecture

Personal Builds & Experiments

Demo

PolyEdge — Prediction Market Council

A multi-agent engine for any Polymarket market. Most prediction bots ask one LLM "what's the probability?" — a dressed-up coin flip. PolyEdge instead assembles a panel of experts tailored to each market — a semiconductor analyst, hedge-fund PM and short-seller for a chip market; a Pentagon advisor and IRGC commander for a conflict — each reasoning in character on a different AI model (via Groq), then weights their consensus and compares it live against the market price. Search any market and watch the council deliberate. Deployed on AWS Lambda + API Gateway.

Adaptive expert panel Multi-model council Edge vs live market Any Polymarket market
Python Multi-agent simulation Multi-model (Groq) AWS Lambda API Gateway Polymarket API
Demo

ev-rag — EV Knowledge RAG

A retrieval-augmented bot for electric vehicles — engineering, brand/model differences, charging, and FSD/autonomy. Ask anything and it retrieves from a 44-source, ~2,950-chunk corpus and answers with inline citations, refusing to fill gaps from general knowledge. Auto-routes queries to metadata filters, balances cross-brand comparisons so neither side is starved, and is validated by a golden-set eval. Runs on local BGE embeddings → Supabase pgvector → DeepSeek, served from AWS Lambda.

44 sources · ~2,950 chunks Cited answers only Supabase pgvector 88% golden-set eval
Python RAG pgvector Supabase DeepSeek AWS Lambda fastembed
Demo

Moodline — Tennis Market Psychology Engine

An experiment in what betting markets miss: the human. Markets price the statistics; Moodline prices the psychology — deterministic signals (fatigue, marathon matches, head-to-head demons, streaks) plus AI agents reading each player's recent headlines nudge the market's devigged baseline by at most ±6%, never overriding it. Picks lock before first serve into an insert-only public board — losses never deleted — and are graded nightly. Backtested on ~48,000 ATP/WTA matches of real closing odds with the honest result published: the market mostly wins, but where the model disagrees hardest the disagreement carried signal, and the market appears to overprice the hot hand.

48K-match backtest Hot hand overpriced Insert-only public picks $0 infra — serverless cron
Python scikit-learn Groq agents Supabase AWS Lambda + EventBridge The Odds API

The AirSprint systems are internal, so there's no repo to click — but I'm happy to whiteboard any of them, tradeoffs included.

Get in Touch