Requirements

Proven Production Experience: Extensive track record of building, deploying, and maintaining machine learning models or LLM-based applications in high-volume production environments.
Advanced Backend Engineering: Mastery of developing scalable microservices and designing APIs, with core proficiency in Python and Kotlin.
Applied AI Engineering & MLOps: Direct experience implementing RAG, fine-tuning methodologies, and prompt engineering. Deep familiarity with LLM frameworks, vector databases, and MLOps tooling to deploy and update models safely.
Data & Infrastructure Expertise: Practical knowledge of building data pipelines, managing feature stores, and structuring data for model consumption and evaluation. Hands-on experience with AWS, containerized services (Kubernetes, Docker), and cloud-native model serving platforms like SageMaker and Bedrock.
Outcome-Driven Technical Leadership: A clear focus on turning technical complexity into tangible business outcomes, such as reducing financial crime investigation handling times and decreasing customer support escalation rates.

What you'll be doing

Drive Architectural Strategy & Scalability: Partner across Data Science, Platform Engineering, and Product teams to design the technical architecture, data pipelines, and orchestration systems required for high-traffic AI services. Ensure the ecosystem supports highly available, low-latency APIs.
Productionize Complex AI Prototypes: Act as the primary technical bridge transforming data science prototypes into customer-facing features. Refactor, deploy, and maintain Python and Kotlin services, including LLM-powered applications and intelligent agents, within production infrastructure.
Design Advanced AI & Agentic Frameworks: Build and optimize application logic surrounding foundational models (leveraging AWS Bedrock and Anthropic). Directly implement advanced techniques, including Retrieval-Augmented Generation (RAG), Model Context Protocol (MCP) servers, and Agent-to-Agent (A2A) orchestration.
Establish Observability & Evaluation Standards: Implement logging, tracing, and metrics frameworks tailored for LLM outputs. Design and execute real-time evaluation frameworks to measure output quality, manage prompt updates safely, and run A/B tests across different models.
Cross-Functional Mentorship: Leverage deep system expertise to identify and recommend new AI use cases based on production feasibility and data availability. Cultivate a collaborative environment centered on mutual learning, knowledge transfer, and code quality across engineering disciplines.

We recognize that our strength lies in our people and the varied perspectives they bring to our workforce. We strive to build talented and diverse teams to drive our business success and empower our people to reach their full potential.
We genuinely welcome and encourage applications from people of all backgrounds, cultures, genders, sexual orientations, abilities, neurodiversities, and ages. We're committed to creating an inclusive workspace where everyone feels valued and respected, free from harassment and discrimination. If there's anything you need to make the application process work for you, please let us know by reaching out to candidate.exp@n26.com.
Visit our website to learn more about Diversity, Equity, & Inclusion at N26.