Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
StructurelyPosted 9 days ago

Staff Engineer — Real-Time Voice AI & Speech-to-Speech

Who we'd reach at StructurelyFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Founder

Decides on early hires

Head of talent

Runs hiring at the company

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a full-time staff or principal engineering role at 21X (formerly Structurely) for an engineer who will design and build real-time speech-to-speech voice AI. It suits engineers with eight or more years of experience who have built streaming audio and voice agent systems and can also lead architecture and mentor others. The role is listed in Austin, Texas, and the posting also names Detroit and remote as options.

What you’ll do

  • Architect native real-time speech-to-speech systems that move beyond speech-to-text, LLM and text-to-speech pipelines.
  • Build semantic endpointing, voice activity detection and conversational turn-taking.
  • Handle barge-in, interruptions, full-duplex audio and natural conversation flow.
  • Reduce latency across streaming audio, inference and time-to-first-audio.
  • Build scalable real-time voice infrastructure over WebRTC, WebSockets, SIP, RTP and telephony networks.
  • Connect real-time voice models with tools, enterprise workflows and orchestration layers.
  • Own architecture, shape the roadmap, mentor engineers and ship production systems.

What they’re looking for

  • Eight or more years of experience building complex production systems
  • Hands-on experience building real-time speech-to-speech voice agents
  • Deep experience with endpointing, voice activity detection, semantic turn detection and interruption handling
  • Strong skills in streaming audio, real-time inference and latency optimization
  • Experience with WebRTC, WebSockets, RTP or similar real-time protocols
  • Strong backend skills in Python, TypeScript or Node.js, Go or Rust
  • Experience building scalable distributed systems
  • A track record of technical ownership and shipping

Nice to have

  • Experience with LiveKit, Pipecat, Vapi, Retell, OpenAI Realtime, Gemini Live, ElevenLabs, Deepgram, Cartesia or similar technologies

What’s on offer

  • Full-time role working directly with the CTO and leadership team
  • Meaningful technical ownership and a hand in building the engineering team

Skills

Speech-to-speech AIVoice AIEndpointingVoice activity detectionTurn detectionStreaming audioReal-time inferenceLatency optimizationWebRTCWebSocketsRTPSIPPythonTypeScriptGoRustDistributed systems

Questions about this role

How many years of experience are needed?

Eight or more years of software engineering experience.

Is the role remote?

The posting lists Austin, Texas, and says the role is also available in Detroit or remote.

Which voice tools are useful to know?

LiveKit, Pipecat, Vapi, Retell, OpenAI Realtime, ElevenLabs and Deepgram are listed as a bonus, not a requirement.