# Kevin G. Henderson

> Full-stack engineer who designs and ships AI agent platforms end to end. Charlotte, NC; Remote (US) only.

I'm Kevin — a full-stack engineer in Charlotte, NC, working remotely. For 20+ years I've taken products from blank repo to production. Lately that means AI agent platforms: the builders, evals, review flows and infrastructure that make LLM features trustworthy enough to run a business on. I adopted agentic coding early, in mid-2025, and it's how I work now.

Availability: Open to Staff / Principal / Founding Engineer roles (Full-time IC, remote (US), occasional travel OK. US citizen, available on short notice. No management tracks.) Also taking select contract & advisory work: https://kevhender.net/work-with-me

## Pages

- [Home](https://kevhender.net/): Positioning, pillars and highlights
- [Experience](https://kevhender.net/experience): Full career timeline
- [Projects](https://kevhender.net/projects): Personal, agent-built projects
- [Resume (HTML)](https://kevhender.net/resume): ATS-friendly HTML resume
- [Resume (PDF)](https://kevhender.net/resume.pdf): Two-page PDF resume
- [Resume (JSON Resume)](https://kevhender.net/resume.json): Machine-readable resume, jsonresume.org schema
- [Resume (Markdown)](https://kevhender.net/resume.md): Plain-text resume
- [How I work](https://kevhender.net/how-i-work): How Kevin ships with coding agents: loop, guardrails, failure modes, numbers
- [Job fit report](https://kevhender.net/fit): Paste a job description; requirement-by-requirement fit with linked evidence
- [How the assistant works](https://kevhender.net/how-the-assistant-works): Design of the "Ask about Kevin" assistant
- [Work with me](https://kevhender.net/work-with-me): Also taking select contract & advisory work: services, engagement formats and process
- [Contact](https://kevhender.net/contact): Email and profiles

## Case studies

- [I built an AI workflow builder — then deleted it](https://kevhender.net/case-studies/deleting-my-ai-feature): From an in-app chat builder to a headless MCP plugin inside Claude and ChatGPT; evals, native tool calling, and knowing when the best UI is someone else's.
- [Measuring LLM features before trusting them](https://kevhender.net/case-studies/evals-for-graph-agent): Deterministic scorers before LLM judges, a simulated user for clarifying questions, grading effects instead of claims, and shadow-testing an LLM's replacement on live traffic.
- [Pausing autonomous agents for a human, durably](https://kevhender.net/case-studies/human-in-the-loop-temporal): How to pause an agent before a consequential action and wait days for a human, without losing state.
- [ZenGRC Pro: from first commit to a ten-engineer product](https://kevhender.net/case-studies/zengrc-pro): Stack choices, a typed GraphQL layer, the Pages-vs-App-Router call, and a redesign with no design team.

## Profiles

- [LinkedIn](https://www.linkedin.com/in/kevhender)
- [GitHub](https://github.com/kevhender)
- [Stack Overflow](https://stackoverflow.com/users/2072693/kevhender)

## Optional

- [Full profile as Markdown](https://kevhender.net/llms-full.txt)