About the role
About the Role
Join an early-stage AI company building an AI coworker for teams. You will develop the runtime and safeguards that help AI agents take useful initiative, work reliably, and handle real tasks safely.
What You'll Do
* Design and build the agent runtime for context gathering, deciding when to act, tool selection, approval, and task completion.
* Write and refine system prompts to encourage useful initiative without noisy or risky behavior.
* Build evaluation and regression tests for real tasks, tool use, and failure cases, and catch regressions as prompts change.
* Improve reliability across long-running work, interruptions, and retries.
* Implement safety boundaries, including approval gates and multi-tenant data separation.
* Work directly with the founding team and early users to shape the product.
What We're Looking For
* Production experience shipping tool-using LLM agents, beyond demos or thin prompt wrappers.
* Hands-on system prompt design, with iterative testing and improvement.
* Experience building evaluation and regression test harnesses for LLM or agent behavior.
* Understanding of safe tool execution, approval workflows, and multi-user data risks.
* Strong ownership across prototyping and production, with the ability to explain technical tradeoffs.
* Experience with LLM agents, tool use, evaluation, and prompt engineering.
Compensation & Benefits
Salary range: $0 to $200,000 USD annually. Founding equity is available; percentage and vesting details are to be determined.
Location
On-site in San Francisco, United States. Candidates should be based in the Bay Area or willing to relocate.