Principal Engineer, Agentic AI Systems

<div class="content-intro"><h2><strong>About Inflection AI</strong></h2> <p>Inflection AI is a Public Benefit Corporation empowering people with human-centered, emotionally intelligent AI. We’re shaping the future of AI by combining emotional intelligence (EQ) and raw intelligence (IQ) to elevate people’s potential.<br><br>Inflection AI created Pi, the world’s first emotionally intelligent AI, to help people work through decisions, emotions, and challenges. Pi is a personal AI agent powered by Inflection AI’s foundation model, proving that AI can be personal, empathetic, and contextually aware.</p></div><h2><strong>About the Role</strong></h2> <p>We're looking for a hands-on Principal Engineer to lead the architecture and technical direction of Inflection's agentic AI systems. You'll build production AI agents that can reason, retrieve context, use tools, and safely execute complex workflows while driving the design of scalable agent architectures, evaluation frameworks, observability, and reliability systems. Partnering closely with product, design, and engineering, you'll turn ambiguous problems into AI-native experiences, mentor senior engineers, and help establish the technical standards that power the next generation of intelligent agents.</p> <p>&nbsp;</p> <p><strong>What You’ll Do</strong></p> <ul> <li>Build production AI agents that can plan, retrieve context, call tools, take actions, and recover from failures.</li> <li>Design agent architectures for task decomposition, tool routing, memory, state management, human approval, and safe execution.</li> <li>Create evals and observability systems for multi-step task success, tool-call accuracy, hallucination resistance, latency, cost, and failure modes.</li> <li>Integrate agents with APIs, databases, SaaS tools, enterprise systems, internal systems, and user-facing workflows.</li> <li>Improve reliability through structured outputs, guardrails, fallback paths, monitoring, permissions, auditability, and human-in-t