Senior Machine Learning Engineer - Credit modelling

PLP Group; Warszawa; Hybrid; PLN 519,000 - 779,000; Full time

Job summary

Klarna, a leading payments company, is hiring a Lead Engineer for the Credit Modeling Pipeline. You will transform models from data scientists into production-ready pipelines and oversee the ML infrastructure across a distributed team in Stockholm, Warsaw, and Milan.

You will write robust production Python, deploy models on AWS SageMaker, monitor performance, and drive end-to-end reliability while collaborating with data scientists and engineers across locations.

Qualifications

• You've written production Python for ML, training models and pipelines.
• You've deployed ML workloads to production on a cloud platform.
• Experience with tree-based models and model monitoring is a plus.

Responsibilities

• Write production Python for credit underwriting models.
• Build and maintain infrastructure for ML pipeline from feature computation to retraining.
• Deploy models into production using AWS SageMaker and ensure reliability.
• Troubleshoot and fix pipeline issues end to end.
• Scale in-house data science capabilities as teams grow.

Skills

Python

ML engineering

AWS SageMaker

CI/CD

Job description

Klarna, briefly At Klarna, we're building an everyday finance network, helping over 120 million consumers across 26 countries save time and money, and worry less about their finances. Working here means taking on problems most companies never get to solve, and being hands-on enough that the interesting part of the work lands with you, not someone else - you'll build with AI, not watch it happen. This is the stretch zone. Come find out what you're capable of.

About the role

Every credit decision Klarna makes runs through a model, and every one of those models runs through a pipeline your team builds and operates. As a Lead Engineer on the Credit Modeling Pipeline team, you'll be the engineer who takes consumer credit underwriting models from a data scientist's experiment to something running reliably in production. This is an engineering position, not a data science one with some engineering on the side. Most of your time goes into writing production code, building the infrastructure the ML pipeline depends on, and deploying models with tools like AWS SageMaker - not developing new modeling approaches from scratch. You'll work alongside a team split between Stockholm and Warsaw, and help scale Klarna's in-house data science capability as the credit risk and fraud teams grow.

What you'll do

• You'll write Python to train credit underwriting models, including tree-based models, and prepare them to run in production.
• You'll build and maintain the infrastructure that supports the ML pipeline - from feature computation through to retraining and monitoring.
• You'll deploy models into production using tools such as AWS SageMaker, and keep them running once they're live.
• You'll troubleshoot and fix pipeline issues end to end, rather than handing them off to someone else.
• You'll help scale Klarna's in-house data science capability as the credit risk and fraud teams grow.

Who you are

• You've written production Python for machine learning - training models, not just prototyping them in notebooks.
• You've taken machine learning models and pipelines from development into production, and owned them once they were live.
• You've worked with tree-based models hands-on, not just studied them in theory.
• You've deployed and operated ML workloads on AWS or a comparable cloud platform.
• You understand the full software development lifecycle - version control, testing, and code review - and apply it to ML code, not just one-off scripts.
• You've worked closely with data scientists, turning their models into pipelines they can rely on in production.
• You communicate clearly in English, spoken and written.

Bonus points for

• You've worked in credit risk, fraud, or another part of financial services, and know the regulatory weight that comes with lending decisions.
• You've built data pipelines at scale inside a larger data science or engineering organization.
• You're familiar with model monitoring or observability tools - drift detection, performance dashboards, and the like.
• You've set up CI/CD for ML deployment.

Things you should know before applying

This position is based in Stockholm or Milan; you'll work alongside a team split between Stockholm and Warsaw.

Working together

We value co-located teams; most teams currently meet in the office 2-3 days per week, and this varies by team and can change over time.

Non-obvious backgrounds are welcome. Diversity of skills, perspectives and backgrounds is how we create, innovate, and disrupt like no other.

Final compensation will be based on the candidate's qualifications, skills, and experience.