Real-Time Voice AI Engineer (Remote)

CloudCraft Labs LLC; Austin (TX); On-site; USD 120,000 - 180,000; Full time

Job summary

CloudCraft Labs LLC is seeking a Voice AI Engineer in Austin with remote work options. You will build and optimize a real-time voice pipeline, handling streaming speech-to-text, language models, and text-to-speech within sub-second budgets.

The role focuses on barge-in, seamless turn-taking, and robust recovery to create human-like agent responses. The ideal candidate has strong Python skills, experience with real-time audio pipelines, and familiarity with latency profiling and STT/TTS/LLM APIs.

Qualifications

• Strong Python experience and real-time audio/streaming pipelines.
• Familiar with latency profiling and low-level performance work.
• Experience with STT / TTS / LLM APIs and tradeoffs.

Responsibilities

• Build the real-time pipeline: streaming STT → LLM → TTS overlapped to a sub-second response budget
• Implement barge-in, turn-taking, and graceful recovery so agents feel human
• Own the WebRTC and telephony transports and the rehearsal sandbox
• Tune latency, prosody, and interruption handling against real call recordings

Skills

Python

Real-time audio

Media pipelines

Streaming systems

Latency profiling

STT/TTS/LLM APIs

Job description

CloudCraft Labs LLC is seeking a Voice AI Engineer in Austin with remote work options. You will build and optimize a real-time voice pipeline, handling streaming speech-to-text, language models, and text-to-speech within sub-second budgets.

The role focuses on barge-in, seamless turn-taking, and robust recovery to create human-like agent responses. The ideal candidate has strong Python skills, experience with real-time audio pipelines, and familiarity with latency profiling and STT/TTS/LLM APIs.