About this role
About the Role
Join an AI product engineering team building a platform that connects data sources and supports real-time workflows. You will shape the platform foundations, helping keep systems reliable, performant, and straightforward to operate as they scale.
What You'll Do
- Integrate AI products that process data from external sources and multiple systems in real time.
- Route streaming responses and language model requests across providers, with fallback and cost controls.
- Monitor latency, costs, and error rates, then address issues proactively before they degrade the experience.
- Make architectural decisions that balance system quality with simple, maintainable designs.
- Build 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 substantial TypeScript experience and ownership of production systems.
- Production experience with Docker and Kubernetes, plus solid knowledge of PostgreSQL, APIs, queues, and caching.
- Strong system design skills and the ability to reason about performance, latency, reliability, and cost trade-offs.
- Experience improving platform reliability and performance under production load, and building observability to diagnose complex systems.
- Experience with streaming responses or language model request routing across providers is valuable.
- Comfort contributing to frontend code when needed, and experience with CI/CD, safe deployments, and incident follow-up is beneficial.
Compensation & Benefits
Annual base salary: €60,000 to €90,000. Visa sponsorship is not available.
Location
Hybrid work arrangement, based in Munich, Germany.