Founding Engineer, Agent

You'll build the AI agents at the heart of Levenza. They take action on someone's behalf instead of waiting to be asked, automating the administrative work enterprises run on, starting with scheduling. The hard part is making them dependable. Memory, context, evals, and model routing under a real cost budget all have to be right, because customers rely on the agents to run their days without added friction, and the bar is software they trust without a human in the loop. That bar applies to the whole system, not just the task in front of you, so you step back to fix root causes instead of symptoms and keep things simple and lean. It's a high-agency, prolific team where you fix issues and improve the process as you see them. Memory that lets agents recall what matters about each person, so they get sharper the more they're used. Context that gives an agent exactly what it needs at the right moment, drawn from a lifetime of calendars, email, and conversations. Proactive agents that act before they're asked, catching the conflict, the gap, the thing no one noticed yet. Background and cloud agents that run for hours on your behalf and resume cleanly, not just when you're typing to them. A model-agnostic platform that routes, caches, evals, and fine-tunes across providers, so each step runs on the best model for the job at the right cost. Secure agent ACL and RBAC that controls what an agent can do, and on whose behalf, at enterprise scale. You might be a fit if You've shipped LLM agents or AI products that real people use, not just demos. You can carry a fuzzy problem across the whole stack, from the interface a user touches to the agent behind it. You care about the product, not just the model. You own the design, the UX, and the whole lifecycle end to end. You reach for the most productive tool for the job, get serious leverage from AI coding agents, and push them as hard as you want since we don't cap token spend. #J-18808-Ljbffr Levenza