About the Role
Join a small, fast-moving engineering team building voice AI agents for customer-facing workflows. You will own projects end-to-end across applied AI, real-time audio, and distributed systems, helping turn complex customer needs into reliable production software.
What You'll Do
Build reliable voice AI systems, including retrieval-augmented generation, dynamic model routing, and evaluation of transcription systems.
Design and operate a distributed call scheduler that manages concurrency, race conditions, time zones, retries, and provider limits.
Extend agents across voice, messaging, and email, maintaining shared memory and state across real-time and asynchronous conversations.
Develop memory and reasoning systems that preserve context through customer workflows.
Build AI-assisted tools for configuring agents, diagnosing issues, and connecting to business systems such as CRMs, calendars, and email.
Improve observability and resilience by making failures traceable and ensuring graceful recovery when calls, workers, or providers fail.
What We're Looking For
Production experience building and owning distributed systems, with a track record of shipping product software and delivering projects end-to-end.
Strong software fundamentals and experience with Python, FastAPI, or TypeScript in production systems.
Experience with real-time systems, audio processing, or voice infrastructure, and with production LLM, AI model, or agentic systems.
Experience with PostgreSQL, Redis, or similar data stores, plus cloud infrastructure on AWS, GCP, or Azure.
Ability to design or debug systems involving concurrency, load balancing, and fault tolerance.
Familiarity with tools such as LiveKit, Temporal, message queues, workflow orchestration, React, and observability platforms is valuable.
Independent, action-oriented approach, sound judgment about code quality and reliability, and a focus on team and customer outcomes.
Compensation & Benefits
€85,000 to €160,000 annually, plus equity. Visa sponsorship is available, and relocation support is offered.
Location
On-site in Berlin, Germany.