About the role
structured by ORILiveKit Engineer (Voice AI) NeuroDrift is a US-based AI voice and enterprise software company. We build real-time voice AI agents that run live on real phone lines, at scale, for enterprise contact centres.
What you will do
- Run and improve our self-hosted LiveKit stack in production: server, SIP service, Egress, Agents workers
- Build and ship voice agents end to end: audio pipeline, STT/TTS, LLM integration, tool calling
- Measure and reduce latency from end-of-utterance to first audio
- Run agent workers on Kubernetes: scaling, graceful drain, deploys during live calls
- Tune turn-taking: endpointing, VAD, barge-in and interruption behaviour
What they are looking for
- 1.5+ years Python, including async (asyncio, FastAPI or similar)
- Self-hosted LiveKit server on Kubernetes
- LiveKit Agents framework in a real deployment
- WebRTC, SIP, RTP fundamentals
- Debugging from logs and metrics
Nice to have
- LiveKit SIP service with a carrier trunk (Telnyx, Twilio, Bandwidth, Vonage or similar)
- LiveKit Egress recording pipelines
- Speech vendor tuning: Deepgram, Whisper, Azure Speech, keyterm biasing, telephony-band audio
- Contact-centre integration: Genesys, Five9, NICE, SIP REFER, transfers
- Noise suppression in a real-time audio path
- Per-minute STT/TTS cost awareness
Full posting text
LiveKit Engineer (Voice AI)
NeuroDrift is a US-based AI voice and enterprise software company. We build real-time voice AI agents that run live on real phone lines, at scale, for enterprise contact centres. Our platform carries production call traffic every day, so latency, telephony quirks and audio edge cases are our daily reality, not a research problem.
We run LiveKit self-hosted on Kubernetes: LiveKit server, SIP service, Egress and LiveKit Agents workers. We are hiring an engineer who has deployed LiveKit, not only built on LiveKit Cloud.
Who this is for
If your LiveKit experience is LiveKit Cloud plus the Agents quickstart, this is not the role. We need someone who has:
- Deployed and run LiveKit server self-hosted on Kubernetes: config, Redis, TURN/ICE, ports and firewalls, upgrades
- Built voice agents on the LiveKit Agents framework and run them as workers: job dispatch, prewarm, load thresholds, graceful drain
What you'll do
- Run and improve our self-hosted LiveKit stack in production: server, SIP service, Egress, Agents workers
- Build and ship voice agents end to end: audio pipeline, STT/TTS, LLM integration, tool calling
- Measure and reduce latency from end-of-utterance to first audio
- Run agent workers on Kubernetes: scaling, graceful drain, deploys during live calls
- Tune turn-taking: endpointing, VAD, barge-in and interruption behaviour
- Debug bad calls across room events, participant tracks, SIP logs and agent logs
What we need
- 1.5+ years Python, including async (asyncio, FastAPI or similar)
- Self-hosted LiveKit server on Kubernetes
- LiveKit Agents framework in a real deployment
- WebRTC, SIP, RTP fundamentals
- Debugging from logs and metrics
Nice to have
- LiveKit SIP service with a carrier trunk (Telnyx, Twilio, Bandwidth, Vonage or similar)
- LiveKit Egress recording pipelines
- Speech vendor tuning: Deepgram, Whisper, Azure Speech, keyterm biasing, telephony-band audio
- Contact-centre integration: Genesys, Five9, NICE, SIP REFER, transfers
- Noise suppression in a real-time audio path
- Per-minute STT/TTS cost awareness
The setup
- Fully remote
- High intensity, 50 to 60 hours a week. Startup pace, not a 9-to-5
- Working hours primarily IST, with availability for US client meetings
This role is for you if you have run LiveKit yourself, not just called it, and want to go deeper on real-time voice in production.
Seniority level: Entry level
Employment type: Full-time
Industries: IT Services and IT Consulting