Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experience. Our AI agents provide intelligent, human-like responses across chat, email, and voice, resolving millions of customer inquiries across every language and at any time.

Since coming out of stealth, Decagon has experienced rapid growth. We partner with industry leaders like Hertz, Eventbrite, Duolingo, Oura, Bilt, Curology, and Samsara to redefine customer experience at scale. We've raised over $200M from Bain Capital Ventures, Accel, a16z, BOND Capital, A*, Elad Gil, and notable angels such as the founders of Box, Airtable, Rippling, Okta, Lattice, and Klaviyo.

We’re an in-office company, driven by a shared commitment to excellence and velocity. Our values—customers are everything, relentless momentum, winner’s mindset, and stronger together—shape how we work and grow as a team.

About the Team

The Agent Orchestration team builds the core execution layer that powers every agent interaction. This includes the systems responsible for coordinating model reasoning, evaluating agent behavior, and ensuring that agents behave reliably in real customer environments.

We focus on correctness, reliability, and speed. Our work shapes how Decagon agents plan, decide, and take actions across millions of interactions.

About the Role

As a Senior Software Engineer on the Agent Orchestration team, you will design and build the systems that determine how Decagon agents operate under real world conditions. You will own complex distributed systems challenges and create foundations that help teams improve agent performance, reliability, and quality.

You will have significant autonomy, direct impact, and the ability to shape the architecture behind one of the most advanced agent platforms in the world.

In this role, you will

Build the execution engine that powers intelligent agents at scale
Design systems that coordinate model reasoning and actions while staying fast and correct
Improve reliability through better testing, observability, and safeguards
Build foundations that help teams evaluate and improve agent behavior safely and continuously

Your background looks something like this

5+ years of experience building production systems
Proficiency in Python or Typescript and comfort with asynchronous programming
Strong debugging skills across complex technical stacks
Ability to design reliable distributed systems that handle real world failure modes
A track record of owning large technical projects end to end

Even better