Greeting and salutations, LiveKit lovers- I'm Wib, and I handle all things tech hiring for JUPUS. We’re betting heavily on Voice AI for the legal sector- law firms are overwhelmed by admin, intake, document handling, and detail-heavy workflows, and we think AI phone agents are about to become a core part of how legal work gets done. At JUPUS, we’re building Marie, our AI Phone Assistant for legal teams, and we’re looking for a Senior AI Voice Engineer to help own and expand the core voice + agent infrastructure behind the product. We need someone who has actually shipped production phone agents handling real users and real conversations — someone comfortable working across the full realtime voice stack: STT → LLM → TTS → telephony. You’ll be building systems that combine: • realtime voice pipelines • LLM agents + tool calling • retrieval systems / RAG • interruption handling + turn-taking • latency-sensitive telephony infrastructure • production orchestration around legal workflows Strong fit if you’ve worked with frameworks/providers like: LiveKit Agents, Vapi, Pipecat, Retell, Bland, Twilio, Telnyx, Deepgram, ElevenLabs, OpenAI Realtime API, Cartesia, Soniox, etc. Especially interested in engineers who: • have personally shipped production phone bots • understand PSTN / SIP / WebRTC tradeoffs • have built LLM-powered systems end-to-end • care about latency, reliability, and conversation quality • enjoy owning systems from prototype → production Small team, high ownership, shipping quickly with real users. The details you're most likely looking for: • Fully remote within ±2h CET timezone (there is no flexibility on the timezone, please do not message me if you're outside it) • English-speaking. • Start ASAP. • Permanent only, no freelance/B2B • Salary budget €100-120k. If you’ve been deep in Voice AI recently, let's talk- drop me a DM here.

Hey @brash-fall-96858 Thanks for sharing this—this is a solid role and very aligned with modern voice AI stacks. I’ve worked on real-time AI voice systems involving STT/LLM/TTS pipelines, tool calling, and latency-optimized conversation flows using platforms like LiveKit, Twilio, and OpenAI Realtime. I’m also comfortable with production considerations around turn-taking, interruption handling, and reliable orchestration in user-facing environments. I’d be happy to learn more about Marie and see how I can contribute.

hey @brash-fall-96858 dmed you in case this role is still open.