Data Scientist

Role Overview

We are looking for a Data Scientist to design, develop, and deploy machine learning solutions that solve business problems. The role involves working across the ML lifecycle — from data analysis and feature engineering to model development, evaluation, and productionisation.

Experience Range:

2 – 4 Years of professional experience

Department / Domain:

Data Science & Analytics (Fintech / Risk / Fraud preferred)

Employment Type:

Full-Time / Permanent

Responsibilities

Develop and deploy machine learning models for classification, regression, and other predictive analytics use cases.

Apply strong understanding of machine learning algorithms including Logistic Regression, Decision Trees, Random Forests, Gradient Boosting models (XGBoost), Ensemble techniques, and Neural networks / deep learning approaches where applicable.

Perform feature engineering, including data preprocessing, encoding, missing value treatment, feature transformations, and creation of meaningful business features.

Analyse large datasets to identify patterns, generate insights, and build data-driven solutions. Evaluate model performance using appropriate metrics such as AUC, Precision-Recall, F1, KS, Gini, and PSI.

Handle real-world ML challenges including class imbalance, model calibration, data leakage, and model performance monitoring.

Build scalable and production-ready ML solutions and collaborate with engineering teams for deployment.

Document models, including objectives, data inputs, performance metrics, and limitations. Stay updated with advancements in machine learning and apply relevant techniques to business problems.

Required Skills & Qualifications

Experience building, improving, and independently scaling machine learning models. Strong foundation in machine learning concepts, statistical frameworks, and model optimization. Hands-on mastery of Python (pandas, numpy, scikit-learn) and SQL databases. Advanced feature engineering capabilities, data preprocessing, and experience handling real-world datasets (including class imbalances and complex workflows).

Deep familiarity with structural model evaluation metrics, workflows, and execution strategies. Exposure to deep learning configurations, sequence models, or transfer learning approaches. Ability to build production-ready ML models, collaborate with engineering teams, and translate complex business problems into effective ML solutions.

Preferred Qualifications

Experience working in fintech, lending, risk, fraud, or other data-intensive domains. Experience with model deployment, monitoring, and ML systems. Familiarity with research papers and emerging machine learning techniques.