As a Member of Technical Staff on Agents, you'll own how our AI Employees reason, use tools, and complete real work. You will be establishing new ways of using AI to do mission critical work in the real world. Areas you may work in: • Agent primitives like the loop, tools, context and more • Iterating on how and when to use models in our products • Complex multi-agent coordination workflows • Optimizing agent behavior for mission critical situations You may be a good fit if you: • Have built agentic products or infrastructure • Have strong software engineering fundamentals and ship production systems • Have taste and strong opinions on model and agent behavior • Make good calls in the gray area, weighing data, user experience, and product judgment when there is no single right answer • Want to work in person in San Francisco Even better: • You've built eval datasets or frameworks to improve an AI system • You stay current on emerging research and bring what works into production • You contribute to open source projects