AI Engineer at N26

on-site · full-time · Visa sponsorship

Apply for this role at N26

Responsibilities:
- Productionize LLM prototypes and AI/agent prototypes into scalable, low-latency services for customer-facing channels.
- Build observability, evaluation, and A/B testing frameworks to measure model output quality and iterate on prompts/models.
- Design and implement data pipelines, orchestration, and APIs to support high-traffic AI features with proper monitoring and failure handling.
- Collaborate with Data Science, ML Engineering, Platform and Product teams to move validated models quickly into production.
- Implement custom application logic around foundational models (e.g., MCP servers, agents) and integrate with managed model platforms (Bedrock/SageMaker/Vertex).

Requirements:
- Proven experience deploying LLM-based applications or AI services to production, with strong focus on reliability and scalability.
- T-shaped skillset: backend engineering (Python and/or Kotlin), applied AI/MLOps, and data engineering understanding.
- Familiarity with cloud platforms (AWS/GCP), containerization (Kubernetes/Docker), and microservice APIs.
- Strong observability/testing skills (metrics, tracing, logging) and experience with RAG, vector DBs, or prompt engineering.
- Ability to work cross-functionally and deliver fast time-to-market while maintaining production standards.