About the job
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.
Responsibilities
Build, lead, and develop a high performing team of engineers, including hiring, coaching, and performance management.
Own the technical strategy and roadmap for Decagon’s orchestration engine, balancing speed of iteration with correctness and safety.
Drive architecture for systems that coordinate complex reasoning and action flows at scale.
Set reliability, testing, and observability standards across the orchestration stack, and build an operating cadence that prevents repeated incidents.
Create frameworks and guardrails that enable fast, safe iteration on agent behavior, evaluation, and rollout.
Partner with Product, Research, and Infrastructure teams to define requirements, navigate tradeoffs, and ship multi-quarter initiatives that move core company metrics.
Qualifications
Minimum
Have 2+ years of engineering management experience leading high performing teams in fast-moving environments.
Have strong technical depth and an IC foundation that enables you to guide architecture, debug complex failures, and make sound trade-offs.
Have experience building distributed systems, execution engines, real-time platforms, or other high scale systems where correctness and reliability matter.
Have a track record of delivering multi-quarter projects through ambiguity, creating clarity for your team and stakeholders.
Care deeply about engineering craft and operational excellence, including testing strategy, observability, and incident learning.
Communicate clearly and collaborate well across Product, Research, and Infrastructure teams.
Preferred
Experience with agent frameworks, runtimes, orchestration logic, or tool use systems.
Experience with evaluation, experimentation, or model quality measurement systems.
Experience building guardrails for safety-critical or highly reliable systems.