Build the self improvement loop end to end, design and build the experience for non-technical people, own sharing and distribution, and develop evaluation infrastructure for AI-powered productivity tools.
$215k to $325k base salary for US-based hires, plus meaningful equity
- Build the self improvement loop end to end: capture evidence from real work, propose improvements, evaluate them, and make the ones that help available for future work.
- Build the skill runtime: discovery, retrieval, loading, and composition inside the agent loop.
- Build the pipeline that turns session history into new skills, new memories, and improvements to existing ones, and the review surfaces where a person accepts, edits, or rejects them.
- Design and build the experience for non-technical people: what Bonsai learned, why it suggests it, and how to review, change, or undo it.
- Build evals for improvements: task suites, graders, and production signals that tell us whether a change helped.
- Nice to have: recommendation systems
- Nice to have: ranking systems
- Nice to have: retrieval systems
- Nice to have: LLM eval infrastructure
