A Data Scientist with banking experience designs predictive models, analyzes financial data, and develops ML/NLP solutions for risk management, fraud detection, and customer analytics. Key responsibilities include building credit risk scorecards, automating data pipelines, and ensuring regulatory compliance, typically requiring 3–5 years of experience with Python, SQL, and statistical modeling in financial institutions. Key Responsibilities * Predictive Modeling & Analytics: Develop behavioural segments, credit risk scorecards, and predictive models for customer onboarding, cross-selling, and churn retention. * Fraud & Risk Management: Utilize advanced analytics to identify anomalies and fraudulent activities in transaction data. Implement risk models (probability of default) and maintain regulatory compliance. * Data Handling: Extract, clean, and analyze structured and unstructured data from internal/external sources. * Technology & Tools: Write advanced SQL queries and Python/R scripts for data manipulation and build machine learning algorithms (e.g., Scikit-learn, TensorFlow). * Stakeholder Communication: Translate complex analytical findings into actionable business insights for management. Required Experience & Skills * Domain Expertise: 3 years of experience in banking or financial services, specifically in credit risk, fraud strategy, or compliance. Need candidates with 3–8 years’ experience in GenAI/Data Science, strong in Python, LLMs (RAG/fine-tuning), NLP, ML model deployment (MLOps), and cloud (AWS/Azure/GCP), with proven delivery in enterprise use cases