Applied AI · Platform engineering · Dallas, TX

Brent Dunham

I build AI systems that hold up in production.

Game developer for 15 years. Now building the platform under the model.

Click a monitor, or press 1 · 2 · 3. The rest of the desk works too.

~/about

Brent Dunham

Principal engineer and engineering leader with 25+ years shipping high-scale software, from healthcare platforms to games with tens of millions of players. Most recently at The Wildcard Alliance I built the studio's applied-AI systems and the real-time platform behind its live-service title. I work on the platform under the model: durable agent runtimes, evaluation people can trust, and the infrastructure that keeps both affordable.

Experience

  1. The Wildcard Alliance2022–2026Principal Engineer
  2. PeopleFun2021–2022Principal Engineer
  3. Playful Corp2013–2021Principal Engineer
  4. Newtoy (acquired by Zynga)2010–2013Principal Engineer
  5. CONEXIS2002–2010IT Architect
  6. Impact Innovation2001–2002Senior Software Architect
  7. KPMG2000–2001Senior Software Architect

Full experience →

Shipped

Words With Friends · Creativerse · Lucky's Tale · Super Lucky's Tale · Wordscapes · Bricks n Balls · Wildcard

~/work

A service for running LLM agents as durable jobs: runs stream to any client, pause for human approval, survive restarts and can be rewound. A research agent over the web and your own documents, with a critic and a citation verifier, measured by an eval harness with a calibrated judge.

briefings with 80%+ of claims cited, after a citation verifier
48% → 95%briefings with 80%+ of claims cited, after a citation verifier
judge agreement with human labels, after recalibration
92%judge agreement with human labels, after recalibration
to re-test a prompt change over 24 runs, by replaying every unchanged model call
$0.90to re-test a prompt change over 24 runs, by replaying every unchanged model call
  • FastAPI
  • LangGraph
  • Postgres
  • Redis
  • React
  • Evals

The Indistinguishability Benchmark

In progress

A multiplayer environment that measures whether AI agents can pass as human players. An eval for agent behaviour, and the same problem from the other side as bot detection.

synthetic-arena

In progress

A Rust and Bevy multiplayer engine where human browser clients and AI agents are the same kind of participant, so the server cannot tell them apart. Netcode over WebTransport with lightyear.

Production AI work

Production

The applied-AI systems I built at The Wildcard Alliance: an LLM content pipeline on IBM Granite, a vision-model captioning service on ChromaDB, agents that playtest builds in CI, MCP servers in daily engineering work, and an adoption program that reached 80% of the team.

Live-service games

Shipped

Words With Friends through its peak growth, Creativerse through years of live operation, Wordscapes for tens of millions of monthly players, and Wildcard, a live-service UE5 title whose viewer platform sustained 10,000+ concurrent viewers per match.

~/writing

Writing

~/contact

Contact

Dallas, TX