We're looking for an AI Voice Engineer who has experience building production-grade real-time voice applications.
This is not a chatbot or simple OpenAI integration project. We're looking for someone who has worked on AI voice systems involving telephony, WebRTC, real-time audio streaming, and AI speech services.
The exact providers you've used don't matter. You may have experience with LiveKit, Twilio, Deepgram, Soniox, ElevenLabs, Cartesia, AssemblyAI, OpenAI Realtime API, Azure Speech, Google Speech, or similar technologies. What's important is that you've built systems with a similar architecture.
What You'll Work On
You'll help build and improve a multilingual AI voice agent that supports both phone calls and web clients through a shared real-time voice pipeline.
The architecture includes:
- LiveKit Cloud
- Twilio Voice / SIP
- WebRTC
- Python LiveKit Agents
- Streaming Speech-to-Text
- OpenAI or similar LLMs
- Streaming Text-to-Speech
- Linux VPS deployment
What We're Looking For
You should have experience with most of the following:
- Building AI voice agents
- LiveKit (Cloud or self-hosted)
- Twilio Voice, SIP Trunking, or Programmable Voice
- WebRTC
- Python
- Streaming Speech-to-Text providers (Deepgram, Soniox, AssemblyAI, Google, Azure, etc.)
- Streaming Text-to-Speech providers (ElevenLabs, Cartesia, Soniox, OpenAI, Google, Azure, etc.)
- OpenAI APIs or other LLM integrations
- Voice interruption (barge-in)
- Turn detection and endpointing
- Low-latency streaming architectures
- Linux deployment and debugging
Bonus Skills
- SIP and RTP troubleshooting
- Voice Activity Detection (VAD)
- Echo cancellation and noise suppression
- Multilingual voice applications
- Production deployment of AI voice systems
When Applying
Please include:
- Examples of AI voice applications you've built.
- Your role in those projects.
- The technologies you used.
- Whether your application supported phone calls, browser clients, or both.
- GitHub, portfolio, demo links, or case studies (if available).
Important: Please apply only if you've previously built or worked on a real-time AI voice application with a similar architecture. Experience with different STT or TTS providers is completely fine—we're looking for someone who understands the overall architecture and production challenges of AI voice systems.
Pay: ₹9,000.00 - ₹20,000.00 per month
Benefits:
Work Location: Remote
