Decagon is looking to improve the real-time systems that enable natural conversations across their conversational AI platform, specifically focusing on the voice agent capabilities to ensure accuracy, responsiveness, and stability at scale.
Requirements
- Proficiency with Typescript, Python, and asynchronous programming
- Experience with asynchronous or streaming systems
- Strong debugging skills across audio, networking, or real time pipelines
- An interest in speech, audio, or multimodal AI
- Experience with speech recognition or synthesis systems
- Experience with VAD, streaming protocols, or other real time audio systems
- Experience designing or maintaining LLM driven applications
Responsibilities
- Build the real time voice runtime that powers natural customer conversations
- Improve speech understanding and synthesis quality while keeping latency low
- Design systems that manage timing, interruptions, and streaming audio reliably
- Create tools that make voice interactions easy to debug, test, and observe at scale
- Collaborate closely with Research to bring new models to production
- Collaborate with Infra to optimize performance
- Collaborate with Product to unlock new conversational capabilities
Other
- 5+ years of experience in software engineering
- In-office company
- Customers are everything
- Relentless momentum
- Winner's mindset
