Senior Data Scientist Transaction Monitoring

The team  

ING’s goal is to enable people to “do their thing” and empower them to stay a step ahead in life and in business. We are one of the largest banks in Europe and we continuously evolve to become one of the most innovative companies in the banking sector. The ING Analytics group is a major driving force in ING’s transformation, aimed at helping us to become a data-driven organization, where advanced analytics is at the heart of our business processes. 

In our tribe COOA, we apply analytics & AI solutions for the Financial Crime & Fraud domains and create advanced analytics applications and models. These models are used to mitigate and to effectively tackle the risk of financial crime for our customers and our society, making us a safer and more compliant bank. Our group consists of more than two dozen data scientists, engineers, data analysts, and customer journey experts, working together to deliver innovative solutions in our domain across multiple countries. 

Roles and responsiblities

As we continue our growth and establishing the added value analytics bring to our domains, we seek to a senior data science profile in order to: 

*     Develop an expertise in applying and deploying machine learning for outlier detection, representation learning, entity resolution, and network & graph applications. 

*     Adopt best practices and quality standards for developing & deploying fit-for-purpose model pipelines, addressing the requirements of the ING model governance. 

*     Be an effective member of a model development & implementation squad, challenge the status quo and build what matters. 

*     Actively learn about our domain, reach out to our stakeholders, and tell captivating stories with our data to create a journey that makes our bank and our society safer. 

Who should apply? 

At ING, we promote diversity not just because it is the right thing to do, but because it’s essential for delivering on our strategy. In order to stay a step ahead we need teams with a healthy mix of contrasting perspectives and backgrounds as they are more creative, faster to adapt and more inventive with their solutions. We strive to hire a workforce as diverse as the communities in which we operate, and we will consider every application, regardless of race, religion, color, national origin, sex, disability or age. 

How to succeed

• You have at least 5 years of (global) work experience in the Data Science space (methods, technology, data) including putting machine learning models into production 

• You have extensive experience in writing production-grade python code that is scalable and deployable to multiple countries 

• You have knowledge of a wide range of machine learning algorithms, ranging from more classical econometric models to cutting-edge neural networks and are able to match them to business problems 

• Experience in applying data science to prevent and detect financial crimes (e.g.  internal/external fraud, money laundering, terrorism financing, tax evasion, …) is a strong plus  

• You can explain complicated subjects clearly 

• You are friendly and approachable and are able to mentor junior data scientists 

• Your enthusiasm is visible and you are good with mobilizing people for our data driven purpose 

• You are motivated to keep on top of the latest developments in data science and software engineering 

• You are able to see where ING can set further steps towards becoming a truly data driven bank. You’re always thinking one step ahead, for example in advising about the best way of implementation. 

• You are a team player who strikes effective balance between independence and acting in the interest of the team 

Experience 

• MSc or PhD with excellent academic results in the field of Computer Science, Mathematics, Engineering, Econometrics or similar is a plus 

• Software engineering and MLOps 

• Machine Learning: Classification, Regression, Clustering, Unsupervised methods, Text Mining. ML models including Random Forests, Gradient Boosting, Neural Networks, Logistic Regression, SVM, KNN, K-Means, etc. Parametric and non-parametric statistics. 

• Programming Languages: Python (including pySpark) 

• Tools: Spark, Hadoop 

• Database handling: SQL, Hive. Familiarity with Oracle, Netezza, HBase, Cassandra, Graph databases. 

• Visualisation tools: D3.js, Shiny, Angular