Work

Selected work

Production LLM systems, Rust infrastructure, applied ML, and the full stack products around them.

01Live demo

Open Switch

LLM gateway with circuit breakers, half-open probes, hedged requests, cost-aware routing, per-key budgets, and request traces.

  • Rust
  • Tokio
  • Axum
  • WASM
Live demo
02Live demo

Screener

Typo tolerant hybrid search with faceted filters that runs fully in the browser.

  • Rust
  • BM25
  • FST
  • WebAssembly
Live demo
03Live demo

Evalgate

LLM evaluation runner with its own YAML check format, flakiness detection, and a pull request gate that writes a Markdown report.

  • Rust
  • CLI
  • YAML
  • WASM
Live demo
04Live demo

Corridor FX

FX exposure and hedging engine with a quantile forecast that is honest about what it cannot predict.

  • Python
  • XGBoost
  • FastAPI
  • React
Live demo
05Case study

Flamide

Multilingual AI agent that answers student enquiries, fills a CRM, and hands off decisions to a counselor.

  • Next.js
  • TypeScript
  • Supabase
  • DeepSeek
06Case study

Sekkin

Schema-first code generator where deterministic structure keeps the LLM focused on application logic.

  • Python
  • FastAPI
  • SQLAlchemy
  • React Flow
07Live demo

Quint

React library for turning chat buttons into explicit decisions.

  • React
  • TypeScript
  • npm
Live demo
08 Research

Representation alignment

Tested the Platonic Representation Hypothesis at toy scale. Reproduced a reference alignment method to 96.37% against a published 96.01%, then recovered unsupervised alignment between independent encoders from a null result to 77.3%.

  • PyTorch
  • Python
  • Research
09 Earlier

Storefront

React and Django store with Stripe PaymentIntents, order tracking, and email notifications driven by Django signals.

  • React
  • Django
  • Stripe
  • REST
10 Earlier

Quild

Interactive 3D building configurator in the browser.

  • React
  • Three.js
  • React Three Fiber