
Founding Harness Engineer
Job Description
About the Role
Join an early-stage AI company building an AI coworker for teams. You will create the agent runtime and reliability systems that help AI act usefully, safely, and dependably in real work.
What You'll Do
Design and build the agent runtime, including how it gathers context, decides when to respond, selects tools, handles approvals, and completes tasks.
Write and refine system prompts so the agent takes useful initiative without being noisy or reckless.
Build evaluation and regression tests for real tasks, tool use, and failure cases, and use them to catch regressions in prompt changes.
Improve reliability across long-running tasks, interruptions, and retries.
Implement safe execution boundaries, including approval gates and multi-tenant data separation.
Work directly with company leadership and early users to develop the product.
What We're Looking For
Typically 4 or more years of relevant experience, with demonstrated ownership of broad technical problems from prototype through production.
Experience shipping tool-using LLM agents to production, beyond demos or thin prompt wrappers.
Hands-on system prompt design, improved through testing and iteration.
Experience building evaluation and regression test harnesses for LLM or agent behavior.
Understanding of safe tool execution, approval gates, and multi-user data separation.
Strong judgment about when an agent should act, ask for approval, or stay quiet, and the ability to explain technical tradeoffs.
Compensation & Benefits
Founding equity is available; percentage and vesting terms are to be confirmed. Local employment or contractor arrangements are to be confirmed.
Location
Remote from Serbia, Poland, or another Eastern European country. Working-hour overlap is to be confirmed.