Senior Data Scientist

We are looking for an experienced Data Scientist to drive the development and deployment of credit risk models, predictive analytics, and machine learning solutions across the lending lifecycle. The ideal candidate combines strong expertise in Python, SQL, statistics, and machine learning with hands-on experience in application, behavioral, and collections scorecards. You will own end-to-end data science initiatives, from problem formulation and feature engineering to model development, production deployment, and continuous performance monitoring.

Responsibilities:

• Design, develop, and optimize credit risk models across the lending lifecycle, including application, behavioral, and collections scorecards.
• Develop predictive models for loan pricing, loss forecasting, and cross-sell opportunities.
• Apply statistical and machine learning techniques, including logistic regression, random forest, gradient boosting, bagging, and dimensionality reduction.
• Evaluate model performance, robustness, interpretability, and business impact.
• Own the complete machine learning lifecycle, including data exploration, preprocessing, feature engineering, model training, validation, and deployment.
• Build scalable training pipelines and support production-grade machine learning implementations.
• Continuously improve model accuracy, stability, and effectiveness through experimentation and iteration.
• Debug data pipelines, model performance issues, and unexpected production behavior.
• Collaborate with Risk, Product, Business, and Engineering teams to identify high-impact data science opportunities.
• Define and execute data science roadmaps aligned with business priorities.
• Identify and integrate internal and external data sources to improve underwriting and risk decisions.
• Translate complex analytical findings into actionable business recommendations.
• Partner with Engineering teams to deploy models into production environments.
• Support model infrastructure planning, implementation, and quality assurance.
• Develop monitoring frameworks and dashboards to track model performance and business outcomes.
• Drive continuous model refinement based on evolving business requirements and data patterns.
• Evaluate emerging machine learning techniques and assess their applicability to business problems.
• Drive technical discussions on modelling approaches, feature selection, and architecture.
• Provide technical guidance, review modelling approaches, and influence data science strategy across teams when operating at lead or staff level.

Requirements:

• 5-10 years of experience in data science, machine learning, or statistical modelling.
• At least 1 year of relevant experience in credit risk, lending analytics, or collections analytics.
• Hands-on experience developing at least one of the following: application scorecards, behavioral scorecards, collections scorecards, loan pricing models, credit loss forecasting models, or cross-sell models.
• Strong programming proficiency in Python and SQL.
• Solid foundation in statistics, probability, hypothesis testing, regression, and feature engineering.
• Practical experience with machine learning algorithms, including logistic regression, decision trees, random forest, and boosting techniques.
• Hands-on experience with Pandas, NumPy, Scikit-learn, or equivalent machine learning libraries.
• Experience building, validating, and improving predictive models using real-world business datasets.
• Strong analytical thinking, problem-solving, and stakeholder communication skills.
• You have built credit risk models that directly influence lending decisions.
• You understand both the mathematics behind predictive modelling and its real-world business application.
• You are comfortable owning machine learning models from experimentation through production.
• You enjoy solving complex lending and risk problems using data.
• You can independently drive projects and collaborate effectively with Product, Risk, and Engineering teams.

Nice To Have:

• Experience with distributed computing tools such as Spark, Hadoop, Hive, or MapReduce.
• Knowledge of TensorFlow, Keras, or other deep learning frameworks.
• Experience with NoSQL databases such as MongoDB, Cassandra, or HBase.
• Exposure to model deployment, monitoring, and production machine learning pipelines.
• Experience using data visualization tools and building model performance dashboards.
• Experience working in high-growth fintech, lending, NBFC, or financial services organizations.