About the Role
Join an early-stage team building agentic software for flexible-work and staffing operations. As the founding engineer for agentic systems, you will own the agent layer end to end and establish how production agents are built, evaluated, and improved.
What You'll Do
Build a context and self-learning system that uses accumulated knowledge to improve agent performance.
Develop self-healing workflows that detect production failures, diagnose their causes, and recover autonomously.
Build and maintain the agent harness and meta-harness for creating, evaluating, and evolving agents quickly.
Set patterns for agent context, tracing, evaluation, and iterative improvement across the product.
Work closely with the technical leadership team, experiment rapidly, and help hire and grow the agent engineering team.
What We're Looking For
Two to nine years of professional software engineering experience and a completed or in-progress engineering, computer science, or quantitative degree from a strong technical university.
Recent experience building agentic software, with a harness-centric approach to context engineering and evaluation-driven iteration.
Experience building context or self-learning systems, agent tracing and evaluations, and autonomous failure detection, diagnosis, or recovery workflows.
A record of shipping working software into production, not research alone, and 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.
Relevant technologies include TypeScript, Effect-TS, PostgreSQL, and large language model agent systems.
Compensation & Benefits
Base salary: $150,000 to $300,000 annually. Visa sponsorship is available.
Location
On-site in San Francisco, California. Candidates based elsewhere in the United States may be considered with a concrete relocation plan to San Francisco.