Careers
Founding Engineer
We're setting the standard for Agent Experience (AX) and helping teams ship something agents want.
Why it matters
The next power user on the web isn't human.
Developer experience took twenty years to become a discipline with tooling, standards and budget behind it. Agent experience won't get twenty years — the shift is happening now, and there's no accepted way to measure it yet. We're building the AX standard and help teams ship agent-ready software.
Your focus
Build at the frontier of agent-first products.
We ship every day, and we're creating a new category. Some ideas on what you might be working on:
- Scaling our evals infra — more agents, more runs, more providers
- Diving deeper into how coding agents think and make decisions
- Improving our methodology so a ranking holds up when a vendor disputes it
- Multi-model coverage: Claude Code, Codex, OpenCode, and every new frontier model
- Building products whose primary user is an agent — our MCP server, tool registry, and feedback CLI
How we work
Small team, high bar.
- Make decisions fast, and revisit them when we're wrong
- Dive deep — accuracy and credibility are the product
- Challenge one another
- Stay curious and have fun