About Risk
The Risk Department safeguards the business by identifying, assessing, and mitigating potential risks across operations and business processes. The team works to ensure a secure, reliable, and trusted experience by strengthening risk management and control mechanisms.
By working closely with cross-functional teams and leveraging data-driven insights, the department proactively manages risk exposure while supporting business growth. With a strong focus on accuracy, prevention, and continuous improvement, the Risk Department plays a critical role in protecting both customers and the company.
About the role
As a Risk Data Scientist, you will drive end-to-end risk data capabilities by processing and managing large-scale datasets, developing fraud/risk models, and enabling automated, real-time risk decisioning to improve accuracy, efficiency, and scalability of DANA's risk systems.
You'll be working on:
- Develop and deploy fraud detection and risk scoring models (supervised and unsupervised) to improve decision accuracy and reduce false positives/negatives
- Design, build, and maintain scalable data pipelines (ETL/ELT) to support risk analytics and real-time decision systems
- Analyze large datasets to identify fraud patterns, anomalies, and emerging risk trends, translating insights into actionable strategies
- Collaborate with Risk, Product, and Engineering teams to integrate models into production systems and decision engines
- Optimize risk decision frameworks through continuous model monitoring, validation, and performance tuning
- Implement data automation solutions to improve efficiency in risk analysis, reporting, and model deployment workflows
- Contribute to risk architecture design, ensuring robustness, scalability, and alignment with evolving business and regulatory needs
Qualifications:
- Strong proficiency in SQL and Python for data manipulation, analysis, and model development
- Hands-on experience in supervised and unsupervised machine learning techniques for fraud/risk use cases
- Solid understanding of data architecture concepts, including ETL/ELT pipelines and large-scale data processing
- Experience in building or supporting risk/fraud models within fintech, banking, or high-transaction environments
- Strong problem-solving skills with the ability to translate complex data into practical risk decision strategies
