Senior AI Engineer | Voice
Jupus · Germany
What this role requires
6 requirements, read out of the advert rather than guessed from the job title:
Also mentioned, not required: AI, PSTN, SIP, WebRTC, OpenAI Realtime, Gemini Live, Deepgram, Soniox, ElevenLabs, LiveKit Agents, Vapi, Pipecat, Retell, Daily Bots, Bland, Telnyx. Worth having, but their absence is not what gets a CV filtered out.
Free, no card. Tells you which of them your CV evidences and which it only implies.
Job description
We’re seeking a driven Senior AI Voice Engineer to join one of the fastest-growing legal tech companies in Europe as we expand our core AI team delivering ‘Marie’, our AI phone assistant.
This role focuses on production voice AI systems operating over real telephony infrastructure : building, maintaining, and scaling phone agents that handle real customer conversations at production volume. You'll own the complete voice stack, from telephony and speech systems through to LLM orchestration, tooling, evaluation, and observability.
Reporting to the AI Lead , you’ll work hands-on from architecture to implementation, collaborating with the Head of Engineering and product teams to ship reliable AI functionality while improving our voice infrastructure, evaluation workflows, and AI platform capabilities.
For an engineer who has personally shipped production phone agents and end-to-end LLM-powered products , this is an opportunity to take technical ownership of Marie, ship quickly, and shape how voice AI evolves across the company.
Your Challenge and Opportunity in This Role
You’ll help define how voice AI is built and operated in a fast-moving product environment. As a core Senior AI Voice Engineer, you’ll turn modern voice and generative AI technologies into production-ready systems that deliver real value to users.
Read the full description (44 more sections)Show less
Your primary goal will be to maintain, improve, and expand our phonebot platform. Expect strong technical ownership, fast iteration, and a clear focus on building reliable voice systems that operate effectively in real-world telephony environments.
Tasks:
AI Strategy & Implementation:
Architect and implement production-ready generative voice AI solutions within our product suite
Develop voice-based AI systems , integrating speech technologies such as ASR/STT and TTS into conversational workflows
Design and optimize real-time voice agent workflows , balancing latency, reliability, and conversational quality
Architect and implement production-ready generative AI and LLM-based solutions to power voice experiences end-to-end
Implement evaluation, testing, and observability for AI systems to ensure reliability and continuous improvement
Establish best practices for AI development, testing, and deployment across products
Handle AI development hands-on as a core technical contributor within a small, fast-moving team where engineers own problems end-to-end and ship quickly
Cross-functional Collaboration:
Work closely with product, design, and engineering teams to integrate AI capabilities into real product workflows
Partner with stakeholders to define and improve user experiences across voice, telephony, and AI-driven interactions
Translate complex AI concepts into practical product features and communicate them clearly to both technical and non-technical stakeholders
Requirements:
Technical Expertise:
5+ years of software engineering experience
1–2+ years of hands-on experience building and operating production Voice AI systems
Proven experience building and shipping production phone agents handling real users and real phone calls
Hands-on experience with at least one major voice-agent framework or provider such as LiveKit Agents, Vapi, Pipecat, Retell, Daily Bots, Bland, OpenAI Realtime, Twilio, Telnyx, Deepgram, Soniox, ElevenLabs, or Cartesia
Strong understanding of the complete voice pipeline, including STT, LLM orchestration, TTS, turn-taking, interruption handling, and latency optimization
Strong understanding of telephony concepts including PSTN, SIP, and WebRTC
Experience building LLM-powered products end-to-end , including prompt engineering, RAG, tool/function calling, model selection, and evaluation
Experience with LLM observability and evaluation tools and designing evaluation pipelines for AI systems
Strong programming skills in Python and solid software engineering practices
Experience implementing AI systems in real production environments , not purely research or academic settings
Nice to Have:
Experience operating high-volume outbound calling systems , including concurrency management, retries, and compliance considerations
Experience deploying OpenAI Realtime API or Gemini Live into production environments
Experience with voice evaluation and observability platforms or custom evaluation frameworks
Fluency or working proficiency in European languages such as German, French, Spanish, or Italian
Experience contributing to or participating in voice AI communities and open-source projects
Note:
You must be located in the CET -2/+2 timezone for this role, and we do not support relocation or visa sponsorship.
Benefits
🚀 Foundational Impact – Help build and scale the core AI capabilities of JUPUS from the ground up
🔒 Technical Ownership – Work directly on the systems powering AI features across multiple products
🌱 Growth Environment – Build production AI systems at the cutting edge of generative AI and agentic workflows
💼 Leadership Visibility – Flat hierarchy with direct access to the Head of Engineering and CTO, reporting to the AI Lead
🏡 Fully Remote – Enjoy the flexibility of working from anywhere
💻 Top Equipment – State-of-the-art MacBook plus all the accessories you need
🏋️ Wellbeing Perks – Urban Sports Club membership to support your healthy lifestyle
If you're passionate about building production voice agents, solving real-world telephony challenges, and creating intelligent AI systems that users rely on every day, we’d love to hear from you.
Find more English Speaking Jobs in Germany on Arbeitnow
You will apply. Then you will hear nothing.
And no one will tell you what was wrong. See it before you send: your ATS score, every weak line, and the fix for each.
- 1
Drop in your CV
One PDF, thirty seconds. No card.
- 2
See what is wrong with it
Every weak passage, quoted from your own CV, with the line to replace it.
- 3
Apply where you fit
Every European role ranked against what your CV actually says.
What's actually stopping you?
- I apply and hear nothing backStart with the ATS scan — see what a filter does to your CV before a human sees it.Start here →
- I can't tell which roles I'd getStart with the match scores — every listing here ranked against what your CV actually says.Start here →
- Just browsing for nowKeep looking. Nothing to sign up for.
- Free, no card
- Your CV file is deleted after parsing
- Refreshed every 6 hours