Senior/Lead Data Scientist-Fraud

Klarna; Stockholms kommun; On-site; SEK 700,000 - 900,000; Full time

Job summary

Klarna, located in Stockholm, is seeking a Data Scientist specialized in building and deploying machine learning models to combat fraud. You will lead projects and maintain existing models while collaborating with diverse stakeholders.

The ideal candidate will have over 5 years of experience in data science, especially in fraud detection, and an advanced degree in a quantitative field. Proficiency in Python and SQL is essential, as is familiarity with AWS and ML modeling packages.

Qualifications

• 5+ years of experience as a Data Scientist or ML Engineer in the financial sector.
• Experience handling large sets of customer data.
• Strong understanding of ML end-to-end processes.

Responsibilities

• Build and deploy ML models to detect fraudulent activities.
• Lead data science projects from problem definition to deployment.
• Monitor and retrain existing ML models in production.

Skills

Machine Learning Models

Python

SQL

Data Science

Fraud Detection

AWS Cloud Computing

Agile Methodologies

Education

Advanced degree in a quantitative field

Tools

scikit-learn

LGBM

Docker

Jenkins

GitHub

Job description

What You Will Do

• Build and deploy ML models to protect Klarna’s customers from fraudulent activities (e.g. account takeover or identity theft fraud).
• Lead data science projects, from problem definition until deployment.
• Monitor, maintain, and retrain existing ML models in production.
• Explore, engineer, and test new potential features to help models in predicting fraud.
• Communicate with stakeholders on conceptual design, development, deployment, and risk control of the model, including writing documentation for external parties.
• Maintain the engineering platform/system used by the team to stay compliant with the company’s requirements.
• Proactive in exploring novel ML/AI products to detect fraud.

Who you are

• Have an advanced degree (Master or Doctorate) in a quantitative field (e.g. statistics, computer science, engineering, mathematics, physics, or related fields).
• 5+ years of experience as a Data Scientist, ML Engineer, or related roles in the financial sector.
• 2+ years of experience working in fraud-related problem space.
• Experience in handling large sizes of customer data (e.g. >100 millions transactions with a few hundreds features).
• Deep proficiency in ML end-to-end process: conceptual design, model development, deployment in production, and monitoring, including pitfalls and tradeoffs to make.
• Deep understanding of business value to deliver: know when an ML solution is needed and when the model is good enough to be deployed for production.
• Good understanding of what metrics to use for monitoring and when to retrain ML models.
• Strong Python and SQL skills, including familiarity with ML modeling packages (e.g. scikit-learn, LGBM) and CI/CD or deployment tools (e.g. Docker, Jenkins, and uv).
• Familiarity with Github and AWS Cloud Computing (Sagemaker, Lambda, S3, Athena, etc).
• Ability to communicate effectively with Analysts, Engineers, and non-technical roles.
• Strong ability to translate business problems into analytical/technical solutions.
• Willingness to collaborate across different locations and time-zones (US and EU), but you will be working at common office hours in your time-zone. Traveling for one or two weeks per year may be needed to meet in-person with other group members.
• Eager to take ownership of a project and deliver results with minimal supervision.
• Agile to adapt to new changes in technology or engineering platforms used by the company.

Awesome to have

• Experience working in payment-related business, e.g. BNPL, credit card, or P2P transfer.
• Technical experience on utilizing Gen AI, Graph Networks, Anomaly Detection, or Behavioral Biometrics into production (beyond just prompting, fine-tuning, or proto-typing solutions).
• Familiarity with AI productivity tools for coding, e.g. Cursor or Github co-pilot.
• Familiarity with compliance and regulation around personal data privacy and model bias.
• Experience in mentoring junior data scientists.
• Experience with inferring the outcome of rejected orders due to fraud suspicion or credit unworthiness.