AI-Focused QA Automation Engineer & Builder
I test, evaluate, and ship AI-powered products — from LLM regression suites to full-stack tools built solo.
Drop a link. Get a week of content.
A multi-channel AI content engine that converts any URL into a Social Post Pack, Blog Post, LinkedIn Carousel, UGC Script, YouTube Short, and Newsletter — generated in seconds.
Benchmarking 4 frontier LLMs on accuracy, tone, latency, and cost.
A promptfoo-based evaluation framework (built and run in VS Code) that tests GPT-4o, GPT-4o-mini, Claude Sonnet 4, and Claude Opus 4 against a history-bot use case. Uses model-graded closed QA and LLM rubric assertions to score factual grounding and tone, plus hard thresholds on latency (<12s) and cost (<$0.08/request).
Three intentionally broken bugs, built to teach by breaking.
Self-contained Playwright projects reproducing real production bug patterns: a UTM parameter lost mid-redirect, a legally required disclosure stripped by a templating bug, and a flaky test pattern shown side by side with its fix.
A token efficiency dashboard for vibe coders.
Tracks burn rate, compares models, and scores prompt efficiency — built for developers who build with AI tools daily and want to know what they're actually spending.
A fully autonomous social content engine for a real fashion brand.
Scrapes trending topics daily, classifies relevance against brand voice, generates captions and imagery with Claude, plans a 7-day calendar, and publishes to Instagram and Threads through the Meta Graph API. Built first for Seed & Berri, architected to scale.
A full sportsbook testing sandbox, built to prove automation depth.
A complete Playwright + TypeScript suite simulating a real sportsbook platform, covering API, SQL, and end-to-end layers with a custom test harness. Built specifically to target iGaming QA roles.
Manufacturing QA for MTA transit infrastructure projects. Inspects laser-cut and fabricated metal components using precision tools.
Executed test cases across devices, conducted cross-browser testing with BrowserStack, and tracked bugs in GitHub with reproduction steps.
Built Promptfoo pipelines and ran 150+ structured LLM regression tests with rubric-based scoring and release thresholds.
10 years embedded QA across one of tech media's most-read publications.
QA lead on editorial and digital product releases.