Data Scientist – Credit Risk and Fraud
MADIFF Polska
IT Services and IT Consulting · 51-200 employees
About the role
Design, maintain, and optimize credit risk and fraud detection models for production banking systems. Collaborate with ML engineers to integrate model outputs into orchestration pipelines while ensuring regulatory compliance and model explainability.
What they look for
Requirements
Requires strong hands-on experience in data science, applied machine learning, and proficiency in Python and SQL. Candidates should have experience with distributed data processing, experiment tracking tools, and working within regulated financial environments.
Benefits
Full description
This is a remote position.
We are looking for a Data Scientist to join an enterprise decision intelligence platform within a global banking environment. The role focuses on credit risk and fraud prevention across multiple international markets, supporting real-time and batch decisioning in production banking systems. The platform combines large-scale structured data processing, machine learning models, and GenAI orchestration layers. It operates at significant scale under strict latency, availability, and regulatory requirements and is continuously expanded with new models, data sources, and reasoning components.
Responsibilities
- Design and maintain credit risk and fraud detection models
- Perform feature engineering on large structured financial datasets
- Train, validate, and optimise machine learning models for production use
- Monitor model performance and implement continuous improvements
- Collaborate with ML engineers on deployment, tracking, and lifecycle management
- Integrate model outputs into LangChain and LangGraph orchestration pipelines
- Ensure model explainability, robustness, and regulatory compliance
- Support documentation and governance requirements in a regulated environment
Requirements
- Strong hands-on experience in Data Science and applied Machine Learning
- Proficiency in Python and common data science libraries (Pandas, NumPy, scikit-learn)
- Experience with gradient boosting frameworks such as XGBoost or LightGBM
- Strong SQL skills and experience working with large datasets
- Experience with PySpark or distributed data processing
- Experience with MLflow for experiment tracking and model management
- Understanding of production model lifecycle and monitoring practices
- Ability to work in regulated or risk-sensitive environments
- Fluent English for professional collaboration
Nice to have
- Experience in credit risk, fraud detection, or financial services
- Exposure to LangChain and LangGraph for orchestration of analytical outputs
- Experience integrating ML models into real-time decision systems
- Understanding of model interpretability and explainability frameworks
Benefits
- Solid, competitive salary
- Work in a multinational environment on international projects
- Comprehensive healthcare
- Long-term B2B contract with a stable project pipeline
- Remote work model
