Own the Voice Channel End-to-End
Architect and build the realtime voice pipeline: STT, TTS, turn-taking, VAD, barge-in, latency tuning
Integrate with telephony, mobile SDKs, and messaging channels (WhatsApp, iMessage, in-app voice)
Design seamless multi-modal handoffs
from voice into camera-based visual sessions and back
Full-Stack Delivery: Ship the mobile and web frontends that capture and render the voice experience
Build the backend services that drive realtime audio, session state, and integration with our agent platform
Make hard calls on protocols, codecs, streaming strategies, and provider trade-offs
Make It Feel Human: Obsess over latency, prosody, interruption handling, and recovery from misrecognition
Build instrumentation that surfaces voice quality issues before users complain
Partner with AI engineers to make sure the agent behind the voice is actually conversational, not transactional
Set the Bar: Define the team’s standards for realtime systems, audio quality, and observability
Mentor engineers across frontend and backend on voice-first thinking

Senior-level experience building voice-based products in the conversational agent space
Strong background across both frontend (mobile and/or web) and backend
Hands-on experience with realtime audio systems
STT/TTS providers, streaming, telephony, or equivalent stacks
B.Sc or higher in Computer Science or a related field

Senior Voice Solutions Architect

Key skills