Senior Voice AI Engineer / Voice Platform Engineer

About the role

Parse AI is seeking a Senior Voice AI Engineer to own the real‑time voice layer of its AI‑powered call‑center platform for hospitality operators. You will be responsible for building a reliable, low‑latency voice pipeline that handles telephony, speech recognition, LLM orchestration, text‑to‑speech, barge‑in, and call transfers.

Key responsibilities

• Design and improve real‑time STT → LLM → TTS pipelines.
• Fine‑tune voice providers such as Deepgram, OpenAI, ElevenLabs, Cartesia, Hamsa, etc.
• Enhance VAD, endpoint detection, silence handling, turn‑taking, and barge‑in behavior.
• Build pronunciation and recognition lexicons for multilingual hospitality vocabularies.
• Work with Twilio Media Streams, SIP trunking, call transfers, and telephony reliability.
• Measure and reduce voice latency across STT, LLM, TTS, network, and telephony layers.
• Debug production voice issues like garbled audio, echo, false interruptions, and failed transfers.
• Scale concurrent call capacity across multiple customers and environments.
• Collaborate with AI and backend engineers to ensure a fast, safe, production‑ready agent experience.

Required profile

• Proven experience building and operating production voice systems.
• Strong background in real‑time voice agents or voice platforms.
• Hands‑on work with STT, TTS, and speech‑to‑speech technologies.
• Familiarity with Twilio Media Streams, SIP trunks, WebRTC, LiveKit, Telnyx, or similar telephony solutions.
• Expertise in voice activity detection, endpointing, barge‑in, and interruption handling.
• Experience handling multilingual or accent‑heavy voice environments.
• Ability to evaluate and tune multiple STT/TTS providers.

Required skills

• Real‑time voice agent development
• Speech‑to‑text (STT) and text‑to‑speech (TTS) integration
• Large language model (LLM) orchestration
• Twilio Media Streams
• SIP trunking
• WebRTC / LiveKit / Telnyx
• Voice activity detection (VAD)
• Endpoint detection and barge‑in handling
• Streaming audio processing and audio buffer management
• Telephony audio formats
• Voice latency measurement and optimization
• Production debugging of phone‑call issues
• Multilingual/accent‑heavy speech system support
• Provider evaluation and tuning across STT/TTS vendors