Senior Voice AI Engineer

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

ABOUT THE ROLE

As a founding engineer on a small conversational AI team, you will own the real-time voice layer, from incoming speech through AI reasoning to spoken responses. You will help make natural, responsive voice interactions work reliably in production, with a focus on end-to-end latency.

WHAT YOU'LL DO

• Build and own streaming speech-to-text, LLM turn-taking, text-to-speech, and telephony or WebRTC transport.
• Measure and reduce latency, targeting first audio under 800 milliseconds on real calls.
• Address interruptions, barge-in, silence detection, overlapping speech, poor audio, accents, and mid-sentence changes.
• Build an evaluation harness from recorded calls, transcripts, and scored turns to detect regressions and guide product decisions.
• Compare voice providers and models through evidence-based testing, and make changes based on results.
• Instrument production systems for turn latency, transcription confidence, drop-offs, and cost per minute.
• Work directly with founders and make technical decisions in a fast-moving team.

WHAT WE'RE LOOKING FOR

• At least 5 years building production software, including 2 or more years shipping voice, speech, or real-time audio systems.
• Experience building and shipping end-to-end real-time voice pipelines, including streaming speech recognition, LLM turn-taking, speech synthesis, and telephony or WebRTC.
• Strong Python or TypeScript skills and comfort working in both.
• Hands‑on experience with an audio stack such as LiveKit, Pipecat, Vapi, Twilio Media Streams, Daily, or a custom WebSocket implementation.
• Experience debugging audio at the frame level, including sample rates, codecs, jitter, and voice activity detection thresholds.
• Experience building LLM evaluation harnesses, optimizing latency against real-world targets, and using evaluation results to make product decisions.
• Clear written English for asynchronous communication. Experience with speech model serving or fine-tuning, SIP, telephony, or LLM orchestration frameworks is a plus.

COMPENSATION & BENEFITS

Compensation is $96,000 USD annually, regardless of location. Visa sponsorship is not available.

LOCATION

Fully remote, anywhere in the world. Core team overlap is 13:00 to 17:00 UTC.