Senior Data Scientist

Job Summary

Responsibilities

• Develop advanced machine learning models using Python on Databricks to solve complex business problems and generate measurable value for clients in retail customer services and utilities domains.
• Design end-to-end data science workflows on Azure Machine Learning that cover data ingestion, feature engineering, model training, evaluation, and deployment in a production-ready environment.
• Collaborate closely with business stakeholders to translate ambiguous analytical needs into clear data science use cases, well-defined hypotheses, and measurable success criteria that align with organizational goals.
• Build scalable data pipelines on Databricks to process large and diverse datasets efficiently, ensuring data quality, consistency, and timely availability for modeling and reporting activities.
• Perform comprehensive exploratory data analysis to uncover patterns, detect anomalies, and derive actionable insights that help improve customer experience, operational efficiency, and risk management.
• Implement robust model validation, performance monitoring, and drift detection practices to ensure that deployed models remain reliable, fair, and relevant over time in dynamic business environments.
• Document analytical approaches, feature definitions, model assumptions, and experimentation outcomes in a clear and reusable manner to support transparency, auditability, and knowledge sharing across teams.
• Collaborate with data engineers, analysts, and product teams to integrate machine learning outputs into digital products, reporting solutions, and decision workflows that are easy to adopt for business users.
• Optimize model training and inference performance on Databricks and Azure Machine Learning by fine-tuning algorithms, managing compute resources effectively, and applying efficient coding practices in Python.
• Apply domain understanding in retail customer services and utilities where available to frame relevant use cases such as demand prediction, churn reduction, pricing optimization, and asset reliability improvement.
• Ensure responsible and compliant use of data by applying privacy-aware design, bias checks, and appropriate anonymization techniques throughout the model development lifecycle.
• Mentor junior data professionals through guidance on coding standards, model design choices, documentation practices, and experimentation strategies to uplift overall team capability.
• Engage with global client teams through hybrid working patterns to present findings, explain model behavior in accessible language, and recommend data-driven actions that support strategic decision-making.

Qualifications

• Demonstrate extensive experience in building and deploying machine learning solutions using Python with strong proficiency in libraries such as pandas, scikit-learn, and relevant deep learning frameworks where applicable.
• Show proven hands-on expertise in Databricks including notebook development, cluster configuration, optimization of Spark workloads, and collaboration using version-controlled environments.
• Exhibit practical experience with Azure Machine Learning including creation of workspaces, pipelines, experiments, model registration, and deployment of services that can integrate with broader enterprise platforms.
• Possess strong understanding of data engineering concepts such as distributed processing, data partitioning, and performance tuning that enable reliable operation of large-scale analytical pipelines.
• Display solid grounding in statistics, experimentation design, and model evaluation techniques that enable rigorous comparison of approaches and trustworthy interpretation of results.
• Communicate complex analytical findings clearly to non-technical audiences through structured storytelling, effective visualization, and context-rich interpretation tailored to stakeholder needs.
• Bring useful exposure to retail customer services or utilities domains that supports problem framing, selection of relevant metrics, and design of solutions aligned with industry-specific challenges.