Founding Engineer, Agents

About the Role Join an early-stage AI company as a Founding Engineer building autonomous agents for complex computer-based work. You will own core systems that help agents execute reliably over extended periods, learn from accumulated knowledge, and demonstrate performance against human-level benchmarks. What You'll Do - Build agents that pursue goals over weeks with minimal or no human intervention. - Design memory systems that help agents retain and use knowledge to improve over time. - Develop evaluation frameworks to determine whether agents outperform people on specific tasks. - Improve agent reliability and reduce the need for human review of individual runs. What We're Looking For - Hands-on experience building production agents that people rely on, with a clear understanding of their failure modes. - Experience with agent memory, long-running execution, multi-step reasoning, and maintaining goal coherence over time. - A track record of building evaluation systems that inform real decisions, including comparisons against human-level baselines. - At least 1 to 2 years at a fast-growing or AI-focused startup, and evidence of substantive engineering work. - Published research that others build on, or software shipped at meaningful scale. - Strong engineering fundamentals and evidence of exceptional problem-solving, such as competitive programming, founding experience, or an equivalent credential. - Agent architecture experience is a plus. A collaborative, kind approach to working through challenging problems is valued. Compensation & Benefits $200,000 to $300,000 annual base salary, with up to $350,000 for exceptional candidates. Meaningful founding equity is available. Visa sponsorship is available. Location On-site, five days a week in San Francisco, California, United States.