Data Scientist

Seeking a hands-on Data Scientist with strong Machine Learning expertise and experience in fraud detection, fraud analytics, anomaly detection, or risk modeling. The ideal candidate will have experience developing, supporting, or optimizing predictive models designed to identify suspicious activities, unusual patterns, and potential risks within large and complex datasets. This role requires strong technical skills, analytical thinking, and the ability to translate data-driven insights into actionable business solutions.
KEY RESPONSIBILITIES
• Design, develop, support, and optimize Machine Learning models for fraud detection, anomaly detection, and risk prediction.
• Analyze large and complex datasets to identify suspicious patterns, anomalies, risk indicators, and emerging trends.
• Develop predictive models using supervised and unsupervised Machine Learning techniques.
• Perform feature engineering, model selection, validation, hyperparameter tuning, and performance evaluation.
• Improve model accuracy while balancing false positives and business impact.
• Collaborate with cross-functional teams, including Data Engineering, Analytics, and business stakeholders.
• Support deployment, monitoring, and continuous improvement of Machine Learning models in production environments.
• Communicate model findings, insights, and recommendations to technical and non-technical stakeholders.
MUST-HAVE REQUIREMENTS
• Professional experience in Data Science, Machine Learning, or Advanced Analytics.
• Strong hands-on experience developing Machine Learning models using Python.
• Previous experience in fraud detection / fraud analytics, anomaly detection, risk modeling, or suspicious activity detection.
• Experience developing, supporting, improving, or optimizing Machine Learning models.
• Strong knowledge of supervised and unsupervised Machine Learning techniques: classification, regression, clustering, anomaly detection, ensemble methods, and gradient boosting (XGBoost, LightGBM, or similar).
• Proficiency with Python, SQL, and relevant libraries such as Pandas, NumPy, and Scikit-learn.
• Experience working with large and complex datasets.
• Strong understanding of feature engineering, statistical analysis, model validation, and performance metrics.
• Ability to communicate technical findings and business implications clearly.
NICE-TO-HAVE QUALIFICATIONS
• Experience in Healthcare, Health Insurance, Financial Services, Banking, Payments, or Insurance.
• Experience with healthcare-related fraud, including claims, billing, payment integrity, or suspicious provider activity.
• Experience with financial fraud, including transaction fraud, payment fraud, identity fraud, credit card fraud, or AML-related analytics.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Knowledge of large-scale data processing platforms such as Spark, Databricks, Snowflake, or BigQuery.
• Experience deploying Machine Learning models into production and working with MLOps processes.
• Familiarity with model explain ability techniques such as SHAP or feature importance analysis.
• Hands-on Data Scientist with practical Machine Learning experience and exposure to fraud, anomaly detection, or risk-related use cases.

Work arrangement
Yes