I help build systems, teams, and software at the intersection of AI systems, product, and evaluation.
- Contract @ Handshake AI — evaluating ChatGPT app development and agent-built software across engineering, logic, design, and product quality
- Founder, Alloway LLC — applied ML products, analytics tooling, and autonomous agent systems
- B.S. Information Science · M.S. Artificial Intelligence — University of South Florida (Magna Cum Laude)
I care about things that still holds up when someone looks closely & over time.
Languages
AI / ML
Backend & APIs
Frontend
Tooling
🪙 SOLVENT — Self-Funding AI Agent
Built for the NVIDIA × Stripe × Nous Research Hackathon
An AI agent that runs as a profitable business. It sells research briefs, collects payment via Stripe, provisions its own compute using its own revenue, and refuses any job that doesn't clear a margin. A fully automated company with its own balance sheet.
Client pays Stripe → Agent earns → Agent fulfils → Agent pays vendors → P&L booked
| Metric | Value |
|---|---|
| Net profit (demo run) | $209.65 |
| Margin | 94% |
| Sponsor stack | NVIDIA Nemotron · Stripe Issuing · NemoClaw guardrails |
⚖️ juryrig
Zero-dependency Python toolkit for auditing LLM-as-judge pipelines — position-bias and verbosity-bias detection, judge panels with agreement scoring, and calibration (Brier, ECE) against human labels.
Full-stack sports analytics platform with live ML predictions, Kelly-based sizing, and a real deployed surface at aiadvantagesports.com.
Repository-quality CLI — scores README quality, CI config, licensing, staleness, and maintenance signals across any GitHub repo.
- Autonomous agent systems with real economic loops (earn, spend, book P&L)
- Evaluation tooling that makes model and app behavior inspectable and trustworthy
- Applied ML products where the evaluation layer is part of the system, not an afterthought
other agents can spend money · SOLVENT runs at 94% margin