1 day ago
Responsibilities
- Design and build the runtime for AI-agent context gathering, action decisions, tool selection, approval, and task completion.
- Write and refine system prompts to encourage useful initiative while limiting noisy or risky behavior.
- Build evaluation and regression test harnesses for real tasks, tool use, failure cases, and prompt changes.
- Improve reliability across long-running work, interruptions, and retries.
- Implement safety boundaries including approval gates and multi-tenant data separation.
- Work with the founding team and early users to shape the product and make technical tradeoffs across prototyping and production.
Requirements
- Production experience shipping tool-using LLM agents beyond demos or thin prompt wrappers.
- Hands-on experience designing, testing, and improving system prompts.
- 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.
Benefits
- Founding equity is available, with percentage and vesting details to be determined.
- On-site role in San Francisco; candidates should be based in the Bay Area or willing to relocate.