About this role
About the Role
Join an early-stage AI company building tool-using agents for teams. You will develop the runtime, evaluations, and safeguards that help agents act usefully and reliably in real-world workflows.
What You'll Do
- Design and build the agent runtime, including context gathering, decision-making, tool selection, approval flows, and task completion.
- Write and iterate system prompts to balance useful initiative with careful, appropriate behavior.
- Build evaluation and regression tests for real tasks, tool use, and failure cases, and use them to catch regressions from prompt changes.
- Improve reliability across long-running work, interruptions, and retries.
- Implement safety boundaries, including approval gates and multi-tenant data separation.
- Work directly with company leadership and early users to shape the product.
What We're Looking For
- 4 to 10+ years of relevant experience.
- Experience shipping production LLM agents that use tools, beyond demos or basic prompt wrappers.
- Hands-on experience designing and testing system prompts, plus building evaluation and regression harnesses for agent behavior.
- Experience implementing safe tool execution, approval gates, and multi-user or multi-tenant data separation.
- Strong ownership across prototyping and production, with the ability to explain technical tradeoffs.
Compensation & Benefits
Base salary up to $200,000 annually, plus founding equity. Equity percentage and vesting details are to be determined. Visa sponsorship information was not provided.
Location
On-site in San Francisco, United States. Candidates should be in the Bay Area or willing to relocate.
Compensation
$200K