About this role
About the Role
Join an AI product engineering team building a platform for integrating data from multiple sources and supporting real-time AI workflows. You will shape the platform foundations, improving reliability, performance, and operational clarity as the system scales.
What You'll Do
-
Integrate AI products that process substantial data across external sources and multiple systems in real time.
-
Route streaming responses and language model requests across providers, applying fallback and cost logic under production load.
-
Monitor latency, cost, and error-rate signals, then act proactively to prevent system degradation.
-
Make architectural decisions that improve system quality while keeping solutions simple and maintainable.
-
Write application code alongside platform and operational work, and investigate production issues through instrumentation and root-cause analysis.
What We're Looking For
-
At least 3 years of production backend engineering experience, including at least 3 years using TypeScript.
-
Production experience with Docker and Kubernetes, plus solid knowledge of PostgreSQL, APIs, queues, and caching.
-
System design skills and the ability to reason about performance, latency, cost, and reliability trade-offs.
-
Experience improving platform performance and reliability under production load, with strong observability and incident-debugging practices.
-
Background working with streaming responses or language model request routing, including provider fallbacks and cost considerations.
-
Experience with application development as well as DevOps or SRE work; comfort contributing to frontend code when needed.
Compensation & Benefits
Base salary: €60,000 to €90,000 annually. Visa sponsorship is not available.
Location
Hybrid in Munich, Germany.