We are looking for an experienced Senior Data Scientist to join our team in Saudi Arabia and work on enterprise-scale data science and AI initiatives.
The role focuses on turning complex business problems and large datasets into predictive, prescriptive, and actionable models, covering areas such as customer intelligence, next-best-action, propensity modeling, recommendation, forecasting, segmentation, collections intelligence, and decision optimization.
Key Responsibilities
• Design, develop, validate, and deploy machine learning and statistical models.
• Lead data exploration, feature engineering, experimentation, model selection, and performance evaluation.
• Develop models for classification, regression, clustering, forecasting, recommendation, propensity, churn, and customer segmentation.
• Translate business problems into measurable data science problems and KPIs.
• Work with Data Engineers to define the datasets, features, and pipelines required for modeling.
• Build robust model evaluation, monitoring, explainability, and retraining approaches.
• Support productionization of models in collaboration with ML/AI and engineering teams.
• Contribute to GenAI initiatives where Data Science intersects with LLMs, RAG, intelligent recommendations, and AI copilots.
• Mentor junior Data Scientists and contribute to data science standards and best practices.
Required Experience
• 5+ years of professional Data Science / Machine Learning experience.
• Strong expertise in Python, SQL, Pandas, NumPy, Scikit-learn and related data science libraries.
• Strong foundations in statistics, probability, experimentation, hypothesis testing, and model evaluation.
• Hands-on experience with supervised and unsupervised machine learning.
• Experience with XGBoost, LightGBM, time-series models, clustering, recommendation systems, and optimization techniques.
• Experience with Spark / PySpark and large datasets is highly desirable.
• Familiarity with Databricks, Snowflake, Azure ML, AWS SageMaker, Microsoft Fabric or similar platforms.
• Understanding of MLOps, model deployment, monitoring, explainability, and feature engineering.
• Exposure to GenAI, LLMs, RAG, and embeddings is a plus, but this is fundamentally a Data Science role rather than a GenAI Engineering role.
