IVR Engineer – Real-Time Voice Pipeline

About the role

You will design, build, and operate production‑grade conversational voice agents that deliver sub‑500 ms latency. The position spans the entire real‑time audio pipeline, tackling the most challenging problems in voice AI, from barge‑in handling to large‑scale streaming coordination.

Key responsibilities

• Build and run conversational voice agents at scale.
• Optimize the real‑time audio pipeline to keep latency below 500 ms.
• Implement voice activity detection (VAD), turn‑taking logic, and barge‑in/interruption handling.
• Integrate and coordinate streaming across Speech‑to‑Text (STT), Large Language Models (LLM), and Text‑to‑Speech (TTS) components.
• Work with multiple languages and frameworks required by the voice stack.

Required profile

• 5+ years of software engineering experience.
• Hands‑on production experience with conversational voice platforms such as Vapi, Retell, ElevenLabs, LiveKit Agents, or Pipecat.
• Deep knowledge of real‑time audio pipelines, including VAD, turn‑taking, barge‑in handling, and streaming coordination with sub‑500 ms latency.
• Polyglot developer comfortable with Go and Python.
• Advanced proficiency in English.

Required skills

• Go
• Python
• Vapi
• Retell
• ElevenLabs
• LiveKit Agents
• Pipecat
• Voice Activity Detection (VAD)
• Turn‑taking logic
• Barge‑in/interruption handling
• Streaming coordination
• 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.
• Provided hardware and software setup for home office.
• Flexible schedule and paid parental leave, vacations, holidays.
• Multicultural environment with mentorship, promotion pathways, and skill‑development opportunities.