The Agent Orchestration team builds the runtime and model orchestration layer that powers Decagon’s agents in production. This is the orchestration layer that turns workflows, tools and guardrails into a reliable, low-latency, and delightful experience for end users.
At the core of this work is the agent harness: the routing, execution logic, tool orchestration, and control-plane systems that determine how an agent behaves in a live conversation. The team owns the full execution lifecycle of each conversation—from selecting workflows and orchestrating multiple models (e.g., router/planner/supervisor patterns), to coordinating tool calls, enforcing safety constraints, and communicating back to the user.
The team operates across both real-time systems (e.g., voice interactions with strict latency requirements) and longer-horizon execution (supporting more complex reasoning and workflows). Our research shows that an agent’s task execution reliability increasingly depends on the orchestration layer that wraps around it.
This is highly experimental, frontier-style engineering. The team continuously analyzes real-world failures, builds feedback loops through offline evaluation and online experimentation, and iterates quickly to improve quality, reliability, and capability. As model capabilities evolve, the team regularly rethinks system design to push agent performance forward in production.
We’re looking for an Engineering Manager to lead the Agent Orchestration team. This is a highly technical, player/coach leadership role at the core of Decagon’s product. You’ll lead the team responsible for the runtime and control plane that powers every agent interaction—coordinating model reasoning, tool use, and evaluation in production—and own the technical strategy and delivery for the orchestration engine behind every customer conversation.
You’ll hire and develop a high-performing team while staying close to architecture, debugging, and reliability. You’ll partner closely with Research, Infrastructure, Product Engineering, and Agent SWE to translate frontier model improvements into predictable, safe, and scalable agent behavior in real customer environments. Success requires strong people leadership, clear execution in ambiguous problem spaces, and the technical depth to drive correctness and operational excellence.