Data Scientist - Machine Learning and Generative AI

Your Opportunity

We are looking for an experienced Data Scientist to join our growing Machine Learning Craft at Mollie. Our Craft is set up as a central entity that provides ML and GenAI capabilities across Mollie. We primarily develop predictive ML models that provide decision intelligence to our colleagues in various Domains such as Monitoring, Payments, Financial Services, and Customer Experience. We also maintain a cloud-based ML Platform, which we use for both model development and production.

In this role, you will be focused on developing ML models for the Monitoring Domain, to tackle challenges in integrity risk, credit risk, fraud detection, transaction monitoring, and more. This is a hands-on role, where you will spend most of your time developing in Python together with our team of DSs and MLEs. You will also be interfacing directly with subject matter experts & stakeholders, e.g. to evaluate the feasibility of potential DS use cases or to explain how your model works during a Team Review.

The Monitoring Domain at Mollie consists of three teams: Credit & Fraud Monitoring, Customer Monitoring, and Transaction Monitoring. As a Data Scientist, you will belong to the Machine Learning Craft, linking you with 10 other Data Scientists & Machine Learning Engineers across Mollie, while working closely with the 3 other Data Scientists dedicated to the Monitoring Domain.

This role is based at Mollie’s new Milan Hub. You will be part of a geographically-distributed team (Amsterdam/Lisbon/Milan) that is comfortable collaborating virtually & hybrid.

What You'll Be Doing

• Develop and maintain ML models for a range of use cases in the Monitoring Domain at Mollie. Ensure these models smoothly reach production and bring measurable value to our stakeholders.
• Perform efficient exploratory data analysis (EDA) and present key insights to colleagues & stakeholders.
• Adopt best practices and standards for the development of robust ML models.
• Collaborate closely with MLEs to prepare your code & model for production using our ML Platform.
• Contribute regularly to our bi-weekly DS Community of Practice (knowledge sharing sessions).
• Help evaluate the feasibility of new use cases for ML in the Monitoring Domain.

What You'll Bring

• 1-3 years experience in data science and machine learning, including the development of models that successfully went to production.
• You are an expert in using applied ML on structured data, in particular regression and classification problems using boosted decision tree (BDT) algorithms.
• You have basic experience with Generative AI, both large language models (LLMs) and embedding models, especially leveraging GenAI in non-chat applications.
• You approach complex problems in a structured way, always looking for the simplest, pragmatic solutions.
• You understand the technical and non-technical constraints of a business problem.
• You are detail-oriented but can also quickly shift priorities if required.
• You enjoy working collaboratively in a cross-functional & distributed team environment.
• You have great presentation skills and can communicate to a wide variety of audiences.
• You have a strong foundation in statistics.
• You have solid software engineering skills and love coding in Python.
• You know your way around a linux shell and are comfortable with Git for version control.
• You know the scikit-learn API inside and out.
• You are comfortable in an agile Way of Working, with Scrum or similar frameworks.

Nice to Have

• Experience with Google Cloud Platform Vertex AI or similar (e.g. SageMaker).
• Experience in the financial services industry (banking or fintech).
• Experience with anomaly detection algorithms.
• Experience with (Py)Spark to handle large datasets.
• Familiarity with DevOps & MLOps principles.
• M.Sc. or Ph.D. in Machine Learning, the natural sciences, or similar.