What you'll do

Design, build and ship production agents on OpenClaw, with tools, memory and guardrails
Connect agents to our systems (identity, payments, games, Discord, Telegram) through MCP servers and APIs
Measure what agents get right and wrong, and close the loop with evals
Turn a manual workflow a team repeats into an agent that does it, end to end
Write the playbooks other teams use to deploy agents safely

What you'll bring

Shipped agent systems in production (OpenClaw, Claude Code, Agent SDKs or similar)
Strong TypeScript or Python; comfortable with APIs, queues and databases
Practical judgement about what an agent should and should not do on its own
You use AI agents to write and review your own code, and can show how

Nice to have

Contributions to OpenClaw or other open-source agent frameworks
MCP server authoring
Experience with Telegram or Discord bots at scale

How you'll work with AI

You will work alongside our own AI agents every day: they draft, test, research and ship with you, and part of your job is making them better.

Where and how

Remote · Taiwan · Hong Kong · Singapore · Dubai (housing benefit) · Toronto. Full-time. We work remote-first with offices in Taiwan, Hong Kong, Singapore, Dubai and Toronto; Dubai roles include a housing benefit.

How to apply

Apply on members.pentagon.games. You'll sign in or create a free Pentagon account first, so your application is saved to it and you can follow or withdraw it. Every application asks one question we care about most: what have you built with AI agents? Show us.

Apply for this role See all roles