Senior Data Scientist

We are seeking a highly skilled Senior Data Scientist to lead advanced analytics projects and deliver end-to-end data solutions. The ideal candidate will have extensive experience turning complex datasets into actionable insights through robust statistical and machine learning models. You will work closely with cross-functional teams (data engineers, analysts, product managers, etc.) to align data science initiatives with business objectives and deliver meaningful, data-driven insights. This role requires strong business acumen and exceptional technical skills, especially in Python programming and cloud-based deployment.

Key Responsibilities

• End-to-End Model Development: Design, implement, and maintain full-stack data science workflows. This includes data ingestion (ETL/ELT), rigorous data preprocessing and feature engineering, model training, validation, and deployment into production. You will refactor and harden data preprocessing pipelines to improve stability and robustness, ensuring reliable data quality and consistency over time.

• Advanced Analytics & Machine Learning: Develop and optimize predictive models (regression, classification, forecasting, etc.) using state-of-the-art techniques. Continuously improve model accuracy by implementing advanced evaluation metrics such as weighted R², adjusted R², correlation coefficients, RMSE, and MAE. Enhance feature selection processes and hyperparameter optimization routines to extract maximum value from data.

• Model Stability & Validation: Perform comprehensive model stability testing and validation. Use fixed random seeds for reproducibility, bootstrap resampling to assess data variability, and temporal hold-out windows to evaluate model decay over time. Analyse feature stability and hyperparameter sensitivity to ensure model robustness across different customer segments, brands, packaging, or markets. Automate the baseline-model validation process to establish repeatable benchmarks and speed up iteration on new models.

• Productionization & Automation: Productionize helper functions and data pipelines. This includes automating calculations (e.g. conversion/redemption rates) and standardizing feature computation so models can be retrained quickly and reliably. Collaborate with data engineers to implement scalable pipelines on Azure (Data Factory, Data Lake, Databricks) and deploy models via CI/CD processes (e.g. using Azure DevOps or similar tools). Ensure solutions adhere to secure coding practices and data governance standards.

• Technical Leadership (Individual Contributor): Act as a subject-matter expert and individual contributor on data science best practices. Write clean, maintainable code in Python (following OOP principles and design patterns) and document workflows in Jupyter Notebooks or VS Code. Stay current with emerging tools and techniques to continuously improve our data infrastructure and methodologies.

• Communication & Visualization: Translate technical results into clear business insights. Create dashboards or reports (e.g. using Power BI, Streamlit, or similar) to present findings to non-technical stakeholders. Provide concise documentation and explanation of model assumptions, limitations, and impacts on business decisions.

Required Qualifications and Skills

• Programming & Technical Skills: Expert proficiency in Python (including OOP and design patterns) for data science. Comfortable coding in Jupyter Notebook and VS Code. Hands-on experience with ML libraries (scikit-learn, TensorFlow, PyTorch) and data libraries (pandas, NumPy). Familiarity with big data tools (Spark, Dask, etc.) and version control (Git).

• Cloud & Deployment: Demonstrated expertise with Azure cloud services for end-toend data solutions. This includes Azure Machine Learning (for model development and deployment), Azure Data Factory (ETL/ELT pipelines), Azure Databricks (data processing), and related services. Ability to architect scalable data pipelines and CI/CD processes in Azure is crucial. Experience with containerization (Docker) and orchestration (Kubernetes) is a plus.

Statistical & Analytical Skills: Deep understanding of statistical modelling, experimental design, and machine learning. Ability to select and apply appropriate evaluation metrics and rigorously validate models to ensure high predictive performance. Familiarity with advanced techniques (e.g. Bayesian methods, time series analysis) is beneficial.

• Business Acumen & Communication: Strong business sense to translate analytical outputs into actionable strategies. Proven ability to collaborate with stakeholders and clearly communicate complex technical concepts to non-technical audiences.

• Soft Skills: Highly organized, proactive problem-solver who thrives in a fast-paced environment. Self-motivated individual contributor with a continuous learning mindset. Attention to detail and commitment to quality in all deliverables.