About the Role
Join an engineering team building an AI platform for business use. You will shape the platform foundations that support reliable, performant AI products and help keep systems clear and maintainable as they handle real-time data and production workloads.
What You'll Do
Integrate AI products that handle data from external sources and multiple systems in real time.
Route streaming responses and LLM requests across providers, using fallback and cost-aware logic.
Monitor latency, costs, and error rates, then act proactively to prevent performance or reliability issues.
Make architectural decisions that improve system quality while keeping designs simple and maintainable.
Build and improve observability, deployment safety, and incident practices to identify root causes and prevent repeat issues.
What We're Looking For
At least 3 years of backend engineering experience, including 3 or more years building production systems with TypeScript.
Production experience with Docker and Kubernetes, plus strong system design skills and sound reasoning about performance, latency, and cost.
Working knowledge of PostgreSQL, APIs, queues, and caching.
Experience improving platform reliability and performance under production load, including instrumentation, observability, and root-cause analysis.
Familiarity with streaming responses or LLM request routing across providers, including fallback and cost considerations.
Experience writing application code alongside DevOps or SRE work; comfort contributing to frontend code when needed.
Knowledge of CI/CD, zero-downtime migrations, rollback-capable deployments, secure defaults, permissions, and structured incident reviews is valuable.
Compensation & Benefits
Base salary: €60,000 to €90,000 annually. Visa sponsorship is not available.
Location
Hybrid work arrangement in Munich, Germany.