I build data systems that ship.
The kind that pay for themselves. Models that keep the accounts worth keeping, aim spend at the customers who convert, and stop losing tests before they cost a quarter. Five live labs below.
Pick a model.
Click anything.
Each card opens a working model. Move the sliders, watch the economics change.
Churn Model
Finds the customers about to leave. Saves revenue already paid to acquire.
Customer Segmentation
Sorts customers by value. Aims spend at the 21% who generate 64% of revenue.
Recommendation Engine
Guesses what they'll watch next. Every basis point of watch-time is a subscription renewed.
A/B Test Simulator
Shows when a "winning" version is real and when it's noise. Stops losing tests early.
Funnel Simulation
Finds the one customer segment quietly killing conversion without breaking the rest.
Dirty data,
clean production.
End-to-end builds, not slideware. Each one shipped with the plumbing, the UI, and the deploy. Usually that's three teams and two quarters of work. Below is what happens when one person owns it.
RiskScore
A vulnerability scoring service that ingests CVE feeds, weights them against deployment context, and emits a single explainable risk score per asset.
Glass Cipher
An intelligence globe that plots open-source signals in real time. Sources are re-weighted by a small language model so clusters resolve into narratives, not noise.
Minecraft Clone
A voxel sandbox built from scratch — chunked world, procedural terrain, block place/break, day-night lighting. Claude Code wrote the engine loop; Python and noise functions shape every biome.
Claude Second Brain
A note graph where Claude backfills links, summaries and open questions. Runs locally against a vault.
Open Claw Mission Control
A control surface for a DIY claw machine. Live camera, queueing, telemetry and a leaderboard.
Assign work to your future self. Re-asks you at the right times instead of at the wrong ones.
Extracts a 5-color palette from any photo with a deliberately slow, gestural picker.
A journal that flags second-order consequences before you commit to them. Prompts pull from your own past entries.
Georgia Institute of Technology
Temple University
Plus 25+ certifications — machine learning (U. Washington), data science (CU Boulder, Duke), people management (Google). full list on linkedin ↗
Let’s build
something.
Best first move: send the job and the numbers it needs to hit. I reply within two business days with relevant examples and code.