About the Role :

We are looking for talented and motivated Data Scientists who are passionate about solving complex fraud-related problems using advanced analytics and machine learning. You will join a high-performing analytics team at NICE Actimize.

What you will do :

- Work with large, complex datasets to analyze fraud cases and identify inconsistencies.

- Build, validate, and optimize machine learning models for fraud detection and prevention.

- Research data patterns to predict fraudulent transactions and improve model performance.

- Enhance existing models using advanced computational algorithms and techniques.

- Develop compelling visualizations that help stakeholders understand trends and insights.

- Collaborate with business teams, engineers, and stakeholders to deliver scalable analytical solutions.

- Drive continuous improvement by staying updated with the latest advancements in Data Science and ML.

- Communicate analytical findings clearly to both technical and non-technical audiences.

- Participate in critical discussions, advocate technical solutions, and support model deployment.

- Contribute to innovation forums and knowledge-sharing initiatives across NICE.

Requirements :

- 4 to 8 years of relevant Data Science experience.

- Advanced degree in Statistics, Mathematics, Computer Science, Engineering, or related fields.

- Strong knowledge of statistical techniques (regression, feature selection, time series, etc.).

- Proficiency in SQL and Excel.

- Strong programming skills in Python (3.7+).

- Hands-on experience with ML techniques (clustering, decision trees, boosting, etc.).

- Experience developing and deploying classification and regression models at enterprise scale.

- Understanding of logistic regression and regularization techniques.

- Familiarity with ML-Ops frameworks or containerized environments (Kubernetes is a plus).

- Experience troubleshooting production data and deployed models.

- Exposure to cloud platforms (AWS, Azure preferred).

- Experience with visualization and presenting insights clearly.

Additional Qualifications :

- Experience in fraud analytics, financial crime, or risk management models.

- Knowledge of financial systems and data standards.

- Experience with containerized model development using Kubernetes.

- Exposure to banking or financial services domain.