Retail Credit Risk Associate

at  N26

ABOUT THE OPPORTUNITY

Are you ready for your next career step? N26 is looking for a Retail Credit Risk Associate to further develop the credit risk function at a cutting-edge technology-driven bank, spearheading the development of our analytical solutions and credit risk models for (Unsecured) Retail Lending, based on state-of-the-art methods and technology, as well as latest regulations in cooperation with leading business and tech experts, and taking a key role in assessing, controlling and reporting credit risks. Modeling experience is required.

SKILLS

• Advanced methodological proficiency: Exceptional analytical skills and a strong foundation in statistical and Machine Learning methods, enhanced by advanced programming capabilities. A deep understanding of statistical modeling, hypothesis testing, and data analysis techniques is essential. Skilled in complex feature engineering, model selection, and optimization to enhance model performance. Understanding of model evaluation metrics specific to credit risk, such as data representativeness, discriminatory power, and calibration accuracy, is a plus.
• Expertise in SQL: Mastery over complex SQL queries, including efficient use of self-joins, window functions, and optimized query performance. Ability to write and execute advanced SQL code, capable of handling extensive datasets for in-depth analysis and model development. Advanced data visualization techniques, experience with Tableau/AWS is a plus. Strong SQL skills. Experience with database management and operations, including working with databases, supporting and maintaining own tables within the schema, and handling schema-related tasks.
• Advanced data manipulation and Machine Learning in Python: Proficient in using Python for sophisticated data wrangling tasks. Expert-level familiarity with pandas, numpy for data cleaning, transformation, integration, and visualization. Strong understanding of Python’s data structures and types to facilitate efficient data manipulation and preparation for model development. Ability to apply and challenge advanced machine learning techniques based on Python libraries like scikit-learn/catboost/xgboost for credit risk modeling.
• Language proficiency: Fluent in English with excellent communication skills. Proficiency in German is considered an advantage

WHO WE ARE

N26 has reimagined banking for today’s digital world. Technology and design empower everything we do and it’s how we are building the global banking platform the world loves to use.
We’ve eliminated physical branches, paperwork, and hidden fees for an elegant digital experience and supreme savings. Giving people the power to live and bank their way is what gets us out of bed in the morning and inspires the work that we do.
We are headquartered in Berlin with offices in multiple cities across Europe, including Vienna and Barcelona, and a 1,500-strong team of more than 80 nationalities.

• Support credit risk model development: In collaboration with Product, Data Science, and Machine Learning Engineers refinement of N26s suite of (unsecured) retail credit risk models (e.g., PD, LGD, CCF, Debt-Servicing Coverage, Early Warning Systems) to support the bank’s strategic growth and risk management excellence. Drive innovation in modeling techniques to enhance accuracy and efficiency.
• Monitor and enhance the credit risk model landscape: Ensure continuous backtesting, monitoring, and improvement of credit risk models using the latest statistical and machine learning methodologies. Ensure models are responsive to dynamic market conditions and aligned with business objectives.
• Perform analysis of credit risk data and contribute to credit risk platform development: Identify trends and insights with further models/reporting optimisation. Participate in the construction and enhancement of a robust credit risk database leveraging both internal and external data sources. Use data with cutting-edge technologies and data analytics practices to automate and optimize credit decisioning, monitoring, and reporting processes.
• Support compliance and best practice adherence: Support the adherence to legal and regulatory frameworks (e.g., GDPR, IFRS9, MaRisk, EBA/ECB guidelines) across all credit risk modeling activities. Support in reviews and updates of the company’s credit policies and procedures.