Lead Data Scientist - Credit Risk Modeling

Overview

In this role you will tackle technically challenging modelling problems in fintech, training transformer-based models on long sequences of real-world transactional data. You will design tokenisation schemes for numerical, categorical, and temporal features and influence how ML operates across Klarna from research to production. You’ll join a small, high-ownership team where your work directly shapes Klarna’s products and ML direction. This is an opportunity to work on scalable, production-grade systems that drive real impact. You will contribute to cutting-edge ML at scale, with a clear mission to advance Klarna’s fintech capabilities.

Responsibilities

• Train and iterate transformer-based models on long sequences of transactional data
• Design tokenisation schemes for heterogeneous feature types (numerical, categorical, temporal)
• Manage the full model lifecycle from data preparation to production serving
• Translate research decisions into scalable ML systems that steer company-wide ML practices
• Collaborate in a small, high-ownership team to deliver impactful ML improvements at Klarna

Key requirements

• Deep understanding of transformer architectures and sequence modelling
• Hands-on experience designing tokenisation schemes for heterogeneous features
• Proficiency in Python, PyTorch, SageMaker, and Airflow
• Experience owning the full model lifecycle from training to production serving
• Comfort working in a small, high-ownership team on open-ended problems

• ownership mindset
• strong problem-solving abilities
• effective collaboration and communication
• Transformer architectures
• Sequence modelling
• Tokenisation for numerical, categorical, and temporal features

Full job description from WhatJobs. Apply for this role →