Senior Real-Time Voice AI Engineer

Zendesk, Inc.; Texas; Hybrid; USD 145,000 - 217,000; Full time

Job summary

Zendesk, Inc. seeks a Senior Full Stack Engineer to build the real-time voice AI product, reducing latency and improving conversation flow. You will ship features across backend systems and web experiences, integrating telephony, WebRTC, and AI/speech services to deliver natural, reliable voice interactions.

The role emphasizes latency, observability, and graceful handoff to humans, with a product-driven mindset and cross-functional collaboration with product, design, and ML teams.

Qualifications

• 3+ years building production software with significant backend engineering experience.
• Experience with real-time or event-driven systems (WebRTC, SIP, streaming APIs).
• Proficiency in Python or equivalent backend languages and async architectures.

Responsibilities

• Design and implement backend services powering real-time voice conversations, focusing on latency, reliability, and observability.
• Build integrations for telephony, WebRTC, real-time audio processing, and external AI/speech services.
• Ship end-to-end product features across backend systems and user-facing web experiences when required.
• Improve platform reliability and performance: monitoring, tracing, autoscaling, and failure recovery.
• Address real-time interaction challenges such as turn-taking, interruptions, responsiveness, and graceful handoff to humans.
• Partner with product and design to deliver voice experiences that feel polished and human.

Skills

Backend fundamentals

APIs design

Async systems

Real-time systems

Python

Latency optimization

Cross-functional collaboration

WebRTC

WebSockets

SIP

Observability

Tools

Telephony stacks

SIP

Media servers

Speech/ASR/TTS integrations

WebRTC

Job description

Zendesk, Inc. seeks a Senior Full Stack Engineer to build the real-time voice AI product, reducing latency and improving conversation flow. You will ship features across backend systems and web experiences, integrating telephony, WebRTC, and AI/speech services to deliver natural, reliable voice interactions.

The role emphasizes latency, observability, and graceful handoff to humans, with a product-driven mindset and cross-functional collaboration with product, design, and ML teams.