Résumé · Currently QA Automation Engineer III
Ben McNulty
AI-Enhanced Senior Software Engineer
Looking for Agent and developer tooling, test and evaluation infrastructure, applied AI engineering, or senior full-stack work on AI-native teams. Florida, USA · Remote · Open to conversations
Summary
I build software across backend, frontend and testing, with a growing focus on how people and AI agents work together. I’m interested in new interfaces that make that collaboration useful and controllable, with the context, clear expectations and verification needed to get reliable work done.
Skills
- AI-assisted development
- Claude Code · OpenAI Codex · GitHub Copilot · Amazon Q Developer · Kiro · Model Context Protocol (MCP) · Multi-agent orchestration · Local LLMs (Ollama)
- Prompt and context engineering
- Prompt engineering · Context engineering · Versioned rules, profiles and prompts · Agent instruction files (CLAUDE.md, AGENTS.md) · Claude Code skills · llms.txt
- Test automation and QA
- Playwright · Selenium WebDriver · C# · .NET · Test architecture · Page Object Model · Cross-browser testing · Regression testing · Accessibility testing (axe-core) · CI/CD · Firebase Emulator
- LLM application development
- LLM integration · OpenRouter · LLM evaluation · Versioned prompt contracts · Model fallback and circuit breakers · Rate limiting · Firebase Functions
- Full-stack development
- TypeScript · JavaScript · React · Next.js · Node.js · PHP · HTML/CSS · REST APIs · SQL (MySQL) · NoSQL (Firestore) · Firebase · Serverless · Git and GitHub
- Front-end, 3D and WebXR
- Responsive web design · Web accessibility (ARIA) · CSS (container queries, oklch) · UI animation · Three.js · WebXR · Hand tracking
- Technical communication
- Technical documentation · Docs-as-code (Markdown) · Code review · Pull-request summaries · Decision logs and handoff notes · Requirements translation · Regression triage · Project scoping and delivery
Experience
QA Automation Engineer III
March 2022–present
- AI-assisted development-tooling point person for an eight-person automated regression testing team: set up Kiro, the team’s current AI tool, and own its supporting tooling, as before for Amazon Q Developer, whose version-controlled Rules, Profiles and Prompts I authored.
- Architected the C# migration of a legacy VB.NET test suite onto a cross-driver adapter that runs Selenium or Playwright under the same test logic; the port is under way.
- Built and shipped an internal documentation and onboarding app that consolidates the team’s scattered docs into Markdown, with a web view built from the codebase.
- Drive weekly regression triage end to end, converting manual test paths into automated tests.
Independent Web Developer · McNulty Web Apps
June 2018–February 2022 · 2012–2014
- Carried responsive full-stack client projects from the first conversation through launch and support, translating ambiguous requests into practical frontend, backend and deployment decisions.
Frontend Engineer · Menuat
February 2016–May 2018
- Shipped digital menu systems from concept to cloud-hosted production, translating brand requirements into responsive, accessible experiences on low-performance, TV-connected hardware.
- Covered project management in the interim, owning scoping, delivery and support across the client base until a permanent PM was hired.
Full-Stack Developer · Enix Networks
September 2012–August 2013
- PHP page servers, contact forms and data handling for client sites.
Personal projects
Non-commercial work on my own site, built with AI coding assistants under my direction and verified by me.
Resilience for a live AI feature (opens in a new tab)
Fallback chain, circuit breaker, layer-specific retries, cost allowlist and a privacy-preserving rate limiter, each traced to a real failure on my own site.
AI Lab: tools for working with AI (opens in a new tab)
Personal tools for recruiter chat, prompt refinement, problem solving and agent configuration, designed around clear expectations and reviewable results.
Orgos: an agent-first organizational OS (opens in a new tab)
A personal agent-first OS I’m building: agent identities, memory, files and flow sequencing live on disk as readable JSON and Markdown, with inference dispatched through an observable queue.
The whole delivery surface, directed and owned (opens in a new tab)
I designed the serverless backend, accessible vanilla-JS frontend, cross-browser tests, media pipeline and gated deploy, and I review and maintain them; AI coding assistants carried out the plans I approved.
Clear expectations for collaborative AI (opens in a new tab)
Versioned prompt contracts, sessions that can be rewound, and clear control states help people guide agents and inspect their work.