Real-Time Voice AI Engineer - Build Conversational Agents

Wati Dot I O; Hong Kong; On-site; HKD 900,000 - 1,300,000; Full time

Job summary

Wati is seeking an Agentic Engineer – Voice AI to design and scale real-time voice AI capabilities for WhatsApp. You will build systems for listening, reasoning, and speaking in real time, integrating frontier AI models and a scalable media pipeline.

You will optimize latency-critical components from audio transport to model inference, and drive orchestration across ASR, LLM, and TTS, collaborating with product teams for production-grade experiences.

Qualifications

• 3+ years of software engineering experience with backend development (Go or Python).
• Experience with real-time communication technologies (WebRTC, RTP/RTCP, audio codecs) or media server infrastructure.
• Familiarity with AI/LLM integration, model APIs, tool calling, or agent orchestration.
• Experience with speech technologies (ASR, TTS, voice activity detection) or audio processing pipelines.
• Understanding of distributed systems, microservices and cloud-native architectures (GCP preferred).
• Comfortable with PostgreSQL, Redis, and pub/sub messaging systems.

Responsibilities

• Design, build, and optimize real-time voice AI pipelines from media transport to LLM inference and speech synthesis.
• Integrate and orchestrate frontier AI models including OpenAI Realtime API and Gemini Live, plus cascade architectures (ASR → LLM → TTS).
• Build and maintain media infrastructure (LiveKit-based routing, Opus codec handling, RTP/RTCP transport, VAD).
• Develop agent capabilities for voice interactions (tool calling, function execution, context engineering, multi-turn management).
• Optimize end-to-end latency across the voice pipeline from audio capture to AI response playback.
• Collaborate with product and platform teams to deliver production-grade voice AI on WhatsApp, across 190+ countries.

Skills

Go

Python

WebRTC

LLM integration

Distributed systems

Troubleshooting latency

Tools

LiveKit

Opus codec

PostgreSQL

Redis

Pub/Sub

OpenAI Realtime API

Google Gemini Live

Job description

Wati is seeking an Agentic Engineer – Voice AI to design and scale real-time voice AI capabilities for WhatsApp. You will build systems for listening, reasoning, and speaking in real time, integrating frontier AI models and a scalable media pipeline.

You will optimize latency-critical components from audio transport to model inference, and drive orchestration across ASR, LLM, and TTS, collaborating with product teams for production-grade experiences.