We're hiring for our partner company, an early-stage startup building an AI coworker: an agent that lives inside a team's everyday tools and actually gets work done. They need a senior Founding Harness Engineer to build the layer that makes it behave. How it pulls in context, when it speaks up, which tool it reaches for, when it stops and asks permission, and how it finishes a long task without falling over halfway. You'll join a seasoned founder and a founding team who spent years building technology in the services world. They watched clients ask for agents long before anyone could deliver them, so they know where the real demand is. The role starts as a contract, with a path to full-time once it's clearly working for both sides. It is remote from Latin America or Eastern Europe, with solid overlap with US Pacific time, since that's where the founder works. If you've shipped tool-using agents to real users and want to build the next one from day one, read on.

Our Culture & Values (read before applying)

We move fast. We take ownership. We work with AI, not against it. And we expect everyone to bring ideas, not wait for instructions.

There are no daily checklists, no micromanagement, and no corporate politics. You get autonomy, trust, and a small team that's always ready to help you grow. Here, impact matters more than titles, and curiosity matters more than seniority.

If you want to level up fast and see your work in real users' hands - welcome aboard.

Responsibilities

• Build the agent runtime: context, tool choice, approval waits, and knowing when to act, ask, or stay quiet
• Write and keep tuning the system prompts. Proactive is great. Spamming the team channel is not
• Own the eval and regression harness. Prompt changes are code, so they get tested like code
• Make long-running work survive interruptions, retries, and the occasional flaky API
• Put the guardrails in: approval gates for risky actions and strict separation between customers' data
• Work directly with the founder and early users, and turn what you hear into shipped behavior

Requirements

• You've shipped tool-using LLM agents to real users in production. Demos and prompt wrappers don't count
• Good instincts for agent initiative, and the test results to back them up
• Hands-on experience building eval and regression suites for LLM behavior
• You understand safe tool execution, prompt injection, and multi-tenant data risk
• Solid backend skills in Python or TypeScript (async jobs, retries, state)
• You take a fuzzy problem from prototype to production and can explain the tradeoffs along the way
• Excellent written and verbal communication; you can explain a tradeoff to a founder or a user without a whiteboard

Nice to have

• MCP, or integrations with tools like Slack, Gmail, Notion, or Linear
• Eval and tracing tools such as Braintrust, Langfuse, or LangSmith
• You've been an early engineer at a startup before and still liked it

Benefits

• A founding seat. You own the agent harness and shape how the product behaves
• Founding equity
• A direct line to the founder and early users, with no layers in between
• Remote from Latin America or Eastern Europe, with solid overlap with US Pacific time
• The tools and models you need to do the job properly
• A small, experienced team that trusts you to run your own work