IVR Engineer – Real-Time Voice Pipeline

About the role

Join a leading global tech services firm to design, build, and operate production‑grade conversational voice agents that deliver sub‑500 ms latency. You will work across the entire real‑time audio pipeline, tackling complex challenges in voice AI such as barge‑in handling and streaming coordination at scale.

Key responsibilities

• Develop and maintain scalable conversational voice agents for multiple languages.
• Optimize the real‑time audio pipeline to consistently meet sub‑500 ms latency targets.
• Implement voice activity detection (VAD), turn‑taking logic, and interruption handling.
• Coordinate streaming between Speech‑to‑Text (STT), Large Language Models (LLM), and Text‑to‑Speech (TTS) components.
• Ensure reliability, performance, and monitoring of production systems.

Required profile

• 5+ years of professional software engineering experience.
• Hands‑on production experience with conversational voice platforms (e.g., Vapi, Retell, ElevenLabs, LiveKit Agents, Pipecat).
• Deep understanding of real‑time audio pipelines, VAD, turn‑taking, and barge‑in handling.
• Comfortable working with multiple programming languages, especially Go and Python.
• Advanced proficiency in English.

Required skills

• Go
• Python
• Vapi
• Retell
• ElevenLabs
• LiveKit Agents
• Pipecat
• Voice Activity Detection (VAD)
• Speech‑to‑Text (STT)
• Large Language Models (LLM)
• Text‑to‑Speech (TTS)

What we offer

• 100% remote work from anywhere.
• Competitive compensation in USD or local currency.
• Hardware and software setup for home office.
• Flexible schedule and paid parental leave, vacations, national holidays.
• Mentorship, career growth, and collaboration with top global talent.