Senior Voice AI Engineer - Remote, Real-Time Audio Stack

Engg; United States; Remote; USD 86,000 - 106,000; Full time

Benefits offered by this job

Fully remote

Job summary

Engg is seeking a founding engineer to own the real-time voice layer from speech input to spoken output on a fully remote, globally distributed team.

You will build streaming speech-to-text, TTS, and the transport stack, while targeting latency under 800 ms on real calls. This role requires hands-on work across live audio, latency optimization, and evaluation harnesses to guide product decisions.

Qualifications

• 5+ years building production software, with 2+ years in voice/real-time audio.
• Experience shipping end-to-end real-time voice pipelines.
• Strong Python or TypeScript; comfortable in both.
• Clear written English for asynchronous communication.

Responsibilities

• Own streaming speech-to-text, LLM turn-taking, text-to-speech, and transport (telephony/WebRTC).
• Measure and reduce latency, aiming for first audio under 800 ms on real calls.
• Address interruptions, barge-in, silence detection, overlapping speech, accents, and mid-sentence changes.
• Build an evaluation harness from calls, transcripts, and scored turns to detect regressions.
• Compare voice providers and models via evidence-based testing and act on results.
• Instrument production systems for turn latency, transcription confidence, drop-offs, and cost per minute.
• Collaborate directly with founders and influence technical decisions in a fast-moving team.

Skills

Python

TypeScript

Tools

LiveKit

Pipecat

Vapi

Twilio Media Streams

Daily

WebSocket

Job description

Engg is seeking a founding engineer to own the real-time voice layer from speech input to spoken output on a fully remote, globally distributed team.

You will build streaming speech-to-text, TTS, and the transport stack, while targeting latency under 800 ms on real calls. This role requires hands-on work across live audio, latency optimization, and evaluation harnesses to guide product decisions.