Credit Risk Modeling Associate - Berlin, Deutschland - N26

N26

Geprüftes Unternehmen

Berlin, Deutschland

vor 3 Wochen

Geschrieben von:

Lena Wagner

beBee Recruiter

Beschreibung

About the opportunity:

Are you ready for your next career step? N26 is looking for a Credit Risk Modeling Associate to further develop the credit risk function at a cutting-edge technology-driven bank, establishing credit risk analytics tools, developing credit risk models based on state of the art data science 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.

In this role, you will:

Be a key contributor to further developing N26 credit risk models (e.g., PD, LGD, CCF, Debt-Servicing Coverage, Early Warning Systems) in order to accommodate N26 growth and risk leadership aspirations
Methodologically support in preparing and executing modeling and calibration steps, evaluating the results, assisting the final model selection and documenting the results including description and motivation of all modeling choices made
Shape credit risk management's enabler role for Banking Products by helping to develop stateoftheart credit solutions for N26's global customer base and supporting new products and markets processes through proper credit risk assessments
Develop, backtest, monitor, and improve credit risk models and decisioning tools, using stateoftheart statistical and machine learning methods together with Data Science
Support building an effective credit risk database from internal and external sources and using latest technologies (e.g., open banking) for automating and improving credit decisioning, monitoring and reporting
Support the implementation and adherence to legal and regulatory requirements (e.g., MaRisk, GDPR, IFRS9) and applicable best practices (e.g., EBA/ECB/BaFin guidelines on internal models and on machine learning) for our credit risk model house in all relevant markets and segments

What you need to be successful:

Background:

You have a quantitative academic background (e.g. applied mathematics, natural science, quantitative finance/economics, statistics/econometrics, engineering) with outstanding grades
MSc, PhD is a plus
You have acquired practical experience in developing credit risk models (PD/LGD/EAD) and a sound understanding of rating systems' design, development, validation, and implementation steps (experience with design of PD Master Scales is a plus)
You know the fundamental elements of retail credit process ranging from credit origination to intensified management and have a comprehensive understanding of credit risk drivers in retail banking P&L as well as a sound knowledge of provisioning (including IFRS9, German GAAP is a plus)
You have a good understanding of the essentials of effective data management, including direct experience of working with relational databases (experience with cloud data warehouse technologies is a plus)

Skills:

Strong analytical and statistical skillset coupled with handson programming experience in SQL and Python (experience with machine learning is a plus)
Great #SQL skill: you easily deal with selfjoins and window/analytical functions, you know how to performs joins efficiently, you can write an optimal SQL code with 100 lines in a reasonable amount of time to fetch the data of interest and curate it for discovery and prototyping
Great data wrangling skills in #python: you are well versed in data types and data structures, pandas is your goto tool when it comes to performing data quality checks and integrating datasets as well as performing other data manipulations for preparing data for developing and calibrating risk models, you can leverage on pandas's functionality for effective data visualization
Applied Credit Risk Modeling skills with #python: you can perform basic feature engineering using pandas & numpy for univariate and multivariate analyses, you have a very strong grip on linear models in #python (e.g., you know how to make a scikitlearn logistic regression model perform similarly to statsmodels), you know how to implement the main metrics for measuring data representativeness, discriminatory power, and calibration accuracy of credit risk models
Entrepreneurial vision, an autonomous attitude, and a 'get things done' approach
Handson approach and eagerness to tackle new topics while demonstrating a quick grasp in conceptual project work and strategic thinking
Fluent English, German is a plus

Traits: