About the Role
Build autonomous AI agents designed to perform complex computer-based work reliably over extended periods. You will own core agent systems, from execution and memory to evaluation, helping advance agents from human-reviewed runs toward dependable autonomous operation.
What You'll Do
Build agents that can work toward a goal over multiple weeks with minimal or no human intervention.
Design memory systems that help agents retain knowledge and improve as they work.
Develop evaluation frameworks to determine whether agents outperform human task baselines.
Improve agent reliability and reduce the need for human review of each run.
What We're Looking For
Hands-on experience building production agents that people rely on, with a clear understanding of their failure modes.
Experience building agent memory, long-running execution, or multi-step reasoning systems that maintain goals over time.
Experience creating evaluation frameworks that inform real decisions and measure performance against human-level baselines.
At least 1 to 2 years of experience at a fast-growing or AI-focused startup.
A record of either publishing research that others build on or shipping software at meaningful scale.
Strong engineering fundamentals; experience designing agent architectures is a plus.
Background in competitive math, programming, debate, games, founding, or an equivalent high-achievement path is valued.
Collaborative approach and conviction in the potential of AI agents.
Compensation & Benefits
$200,000 to $300,000 annual base salary, with up to $350,000 for exceptional candidates. Meaningful founding equity is offered. Visa sponsorship is available.
Location
On-site in San Francisco, California, five days per week.