Senior AI Engineer | Voice

About Jupus: Jupus is one of the fastest-growing legal technology leaders in Europe, on an ambitious mission to transform automated client communication through next-generation conversational intelligence. Our flagship platform deploys ‘Marie’, a highly advanced AI phone assistant purpose-built to operate over real telephony infrastructures and handle real customer conversations at a production volume. By combining cutting-edge generative audio models, real-time speech-to-text pipelines, and legal domain context, Jupus eliminates old-fashioned manual call queues and entry-level phone triage scripts—enabling law firms and corporate legal entities across Europe to provide instant, empathic, and highly secure 24/7 coverage.

Position Overview

We are seeking a highly autonomous, systems-fluent, and audio-proficient Senior AI Engineer | Voice to take comprehensive technical ownership of our core conversational voice stack under a permanent, full-time remote layout open across Germany and the United Kingdom. In this high-leverage machine learning and platform engineering seat, you will act as a principal contributor building, maintaining, and scaling phone agents that process live conversations over enterprise telephony networks. Shifting completely away from routine non-regulated administrative transcription data entry, basic visual website template layout adjustments, or standalone copy typing, you will run an active real-time WebRTC streaming, LLM orchestration, and low-latency audio processing laboratory. Reporting directly to the AI Lead and collaborating alongside the Head of Engineering, you will own the voice stack end-to-end. This position requires an engineering authority with 5+ years of software history who maps intelligent audio agent workflows fluidly natively using AI Engineer and voice primitives, commands production experience with conversational frameworks, and designs rigorous evaluation pipelines within a CET -2/+2 timezone window.

Key Responsibilities

• Voice Stack Architecture Governance: Architect, implement, and maintain production-ready generative voice solutions and real-time phone agents natively utilizing AI Engineer principles.
• Speech Technology Integration: Build and optimize streaming workflows integrating advanced Automatic Speech Recognition (ASR/STT) and Text-to-Speech (TTS) nodes into low-latency conversational models.
• LLM Orchestration & RAG Engineering: Design and fine-tune complex LLM pipelines, prompt engineering matrices, Retrieval-Augmented Generation (RAG) loops, and functional tool-calling parameters to govern conversational flow.
• Telephony Pipeline Optimization: Structure audio streaming engines to seamlessly handle conversational turn-taking, interruption detections, jitter bugs, and minimal latency overhead across PSTN, SIP, and WebRTC frameworks.
• Observability & Evaluation Systems: Formulate, implement, and monitor comprehensive automated testing and observability pipelines to benchmark voice quality and conversational metrics.
• Cross-Functional Feature Syncing: Collaborate face-to-face alongside distributed Product, Design, and Core Engineering squads to translate intricate audio-model concepts into reliable product features.
• Hands-on Software Craftsmanship: Serve as a core technical contributor inside an agile team, writing maintainable production-grade Python backend logic to solve problems end-to-end.

Required Skills & Qualifications

• A minimum of 5+ years of proven, successful professional history operating within a Senior AI Engineer, Voice Platform Developer, Speech Systems Architect, NLP Engineer, or closely matching high-scale machine learning capacity.
• A minimum of 1–2+ years of direct, hands-on experience building, launching, and maintaining production-grade Voice AI phone agents handling real users over telephone lines .
• Expert Audio Framework Command: Practical production fluency operating with at least one major voice-agent provider or framework (such as LiveKit Agents, Vapi, Pipecat, Retell, Daily Bots, Bland, ElevenLabs, or OpenAI Realtime API ).
• Advanced technical literacy utilizing Python backed by solid software engineering principles, modular code styling, and production environment sanitation rules.
• Outstanding written and verbal communication strengths in English, with an established history explaining complex architectural trade-offs to non-technical stakeholders.
• Timezone & Location Context: Position operates under 100% remote parameters open exclusively to qualified engineers residing permanently within Germany or the United Kingdom, and strictly located inside the CET -2/+2 timezone corridor .

Preferred Strategic Indicators (Nice to Have)

• Prior technical experience operating high-volume outbound calling systems, including concurrency tuning, automated retries, and regional telecom compliance structures.
• Familiarity or production exposure deploying Gemini Live, custom voice evaluations, or building custom audio analytics dashboards.
• Professional working proficiency or conversational literacy in additional European languages (such as German, French, Spanish, or Italian) to augment local localization tracks.

What We Offer

• Competitive European AI Engineering Compensation Matrix: A highly competitive annual salary package calibrated precisely to your machine learning and voice architecture history, supplemented by cutting-edge tooling allowances.
• 100% remote workspace infrastructure autonomy anywhere within Germany or the United Kingdom, ensuring top-tier flexibility.
• Foundational AI Team Ownership: Unique professional milestones built by serving as a core voice engineer shaping the primary phonebot platform for a rapidly expanding legal tech pioneer.
• Access to elite provided equipment, featuring a state-of-the-art MacBook alongside all required high-performance remote office accessories.
• Comprehensive health preservation benefits, localized wellbeing perks including an Urban Sports Club membership to support a healthy lifestyle, a flat organizational hierarchy, and direct collaboration channels next to the CTO and Head of Engineering.