Software Engineer, Voice Agent

Decagon AI, Inc.; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

A leading company in AI is seeking a Software Engineer for the Voice team. You will architect the infrastructure powering millions of voice interactions, developing cutting-edge solutions that enhance user experiences. Ideal candidates will have extensive software experience, proficiency in Python and Typescript, and a passion for solving complex challenges.

Benefits

Medical, dental, and vision benefits

Flexible vacation policy

Daily meals in the office

Qualifications

• 5+ years of industry experience in software engineering.
• Proficiency with Python and Typescript.
• Comfort digging into system failures.

Responsibilities

• Develop techniques for evaluating speech-to-text and text-to-speech models.
• Architect highly asynchronous systems for audio and text data.
• Build automation to monitor and detect issues across calls.

Skills

Python

Typescript

Asynchronous programming

System failures analysis

Multi-modal models

Job description

About Decagon

Decagon is building the most advanced conversational AI agents for the enterprise. Since starting the company, we've been on a tear, winning over customers like Duolingo, Notion, Rippling, Eventbrite, Webflow, BILT and many more. Our AI agents provide a human-like customer support experience that enables enterprises to better serve their customers and efficiently manage their customer experience organizations.

We've raised $100M in total funding from Bain Capital Ventures, Accel, a16z, BOND Capital, A*, Elad Gil, and notable angels, including the founders of Box, Airtable, Rippling, Okta, Lattice, and Klaviyo.

About the Team

The Voice team at Decagon builds AI voice agents that don't just answer questions—they understand context, respond with genuine empathy, and solve complex problems with surgical precision.

Our mission is to deliver magical support experiences — AI agents working alongside human agents to help users resolve their issues.

About the Role

On the Voice team, you’ll architect and build the lightning-fast infrastructure that powers hundreds of millions of voice interactions annually. You will develop cutting-edge methods to orchestrate high intelligence models within extreme low-latency constraints.

Engineers here own their work end-to-end and are trusted to make a real impact. This role is for someone who dives deep into complex system challenges, builds elegant solutions that scale to millions of users, and creates automation that prevents problems before they happen.

In this role, you will

• Develop techniques for evaluating state of the art speech-to-text, text-to-speech and other audio models

• Architect highly asynchronous, multimodal systems that operate on both audio and text-based data

• Build automation that monitors and detects intermittent issues across hundreds of millions of calls

Your background looks something like this

• Have 5+ years of industry experience in software engineering

• Proficiency with Python, Typescript and asynchronous programming

• A high degree of comfort digging into systems failures within deep technology stacks using any tool necessary

• Prior experience working with multi-modal models

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