InterviewStack.io LogoInterviewStack.io
Browse more Software Engineer jobs

Senior Software Engineer, Agent Orchestration

Decagon

San Francisco$330 - $250,000senior7 months agoAI-enriched
57 views18 saves9 applies

Prepare for this role


Benefits

EquityHealth InsuranceDental & VisionUnlimited PTOPaid Time OffStock Options

Job Type

full time

Description

About Decagon

Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experiences.

Our technology enables industry-defining enterprises like Avis Budget Group, Block’s Cash App and Square, Chime, Oura Health, and Hunter Douglas to deploy AI agents that power personalized, deeply satisfying interactions across voice, chat, email, SMS, and every other channel.

We’re building a future where customer experiences are being redefined from support tickets and hold music to faster resolutions, richer conversations, and deeper relationships. We’re proud to be backed by world-class investors who share that vision, including a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, along with many others.

We’re an in-office company, driven by a shared commitment to excellence and velocity. Our values — Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle — 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

  • Experience with real time or low latency systems

  • Experience with workflow engines, agents, or model driven applications

  • Experience building tooling or infrastructure for other engineers

  • Experience with experimentation or evaluation systems

Benefits:

  • Medical, dental, and vision benefits

  • Take what you need vacation policy

  • Daily lunches, dinners and snacks in the office to keep you at your best

Compensation

$250K – $330K + Offers Equity

This job is found at InterviewStack.io

Skills

agentsasynchronous programmingdebuggingdistributed systemsevaluation systemsexperimentationfault toleranceinfrastructurelow-latency systemsmodel reasoningobservabilitypythonreal-time systemsscalabilitysoftware architecturetestingtoolingtypescriptworkflow engines

About Decagon

Decagon is a company with job postings primarily for roles such as Enterprise Solutions Engineer in Latin America. The company uses the Ashby ATS platform for recruiting. Specific details about its industry, size, and headquarters are not publicly available from the provided context.