3 hours ago
Base Salary
$150k - $300k/yr
Responsibilities
- Build context and self-learning systems that improve agent performance through accumulated knowledge.
- Develop self-healing workflows that detect production failures, diagnose causes, and recover autonomously.
- Build and maintain agent harnesses and meta-harnesses for creating, evaluating, and evolving agents.
- Establish patterns for agent context, tracing, evaluation, and iterative improvement across the product.
- Collaborate with technical leadership, experiment rapidly, and help hire and grow the agent engineering team.
Requirements
- Two to nine years of professional software engineering experience.
- Completed or in-progress engineering, computer science, or quantitative degree from a strong technical university.
- Recent experience building agentic software using a harness-centric approach to context engineering and evaluation-driven iteration.
- Experience with context or self-learning systems, agent tracing and evaluations, and autonomous failure detection, diagnosis, or recovery workflows.
- Record of shipping working software into production rather than research alone.
- Experience building reusable agent harnesses is valuable.
- Strong early-stage startup experience as a funded founder or engineer at a venture-backed pre-seed, seed, or Series A company.
Benefits
- Base salary is $150,000 to $300,000 annually.
- Visa sponsorship is available.
- On-site in San Francisco, California.
- Candidates elsewhere in the United States may be considered with a concrete relocation plan to San Francisco.