Senior Data Scientist

What You'll Do :

• Initial focus will be on automating forecasting and scenario simulation processes for Sales, Finance, and Commercial Support; future scope may extend to other CBS functions.
• Identify further business problems across Purchasing, Finance, Logistics, Sales Administration, and Personnel that can be solved through statistics, machine learning, or AI.
• Collect, clean, and prepare large structured and unstructured datasets; run exploratory data analysis to uncover patterns, trends, and business opportunities.
• Develop, train, validate, and optimize machine learning models for predictive and prescriptive analytics.
• Build and maintain data science solutions using Databricks and Azure ML Studio, collaborating with Data Engineers to prepare data, develop features, and industrialize analytical and machine learning use cases.
• Deploy and monitor machine learning models in production, evaluating performance with appropriate statistical metrics and retraining as needed.
• Communicate analytical findings and forecast outputs to technical and non-technical stakeholders, including Sales and Finance leadership, through clear visualizations and presentations.
• Support AI-driven process automation by integrating predictive models into business workflows, working cross-functionally to keep solutions aligned with business goals.
• Document models, assumptions, methodologies, and analytical processes according to company standards.

How You'll Work :

Stakeholder Communication

• Translate complex business data into actionable insights and forecast recommendations for Sales, Finance, and commercial support teams.
• Explain model and forecast performance, assumptions, and limitations clearly to both technical and non-technical audiences.

Model Governance & Data Quality

• Build reliable, interpretable models, and monitor for concept drift or performance degradation as forecast cadence increases.
• Ensure reproducibility through version control, documentation, and experiment tracking.
• Apply company standards for data quality, security, privacy, and governance, validating data sources before model development.

Continuous Learning & Collaboration

• Stay current with advances in data science, AI, and machine learning, and bring new ideas to the team.
• Share knowledge with colleagues through documentation, code reviews, and mentoring.

What You'll Bring:

• 2–5 years of experience as a Data Scientist, Machine Learning Engineer, or in a similar analytical role.
• Hands-on experience with Databricks and PySpark for scalable data processing, and strong Python programming skills (including Pandas, NumPy, and scikit-learn) for developing, training, and evaluating machine learning models.
• Good knowledge of machine learning techniques, including regression, classification, clustering, recommendation systems, time-series forecasting, and anomaly detection.
• Solid understanding of statistics, probability, hypothesis testing, and experimental design.
• Experience with data preprocessing, feature engineering, feature selection, model evaluation, hyperparameter tuning, and cross-validation.
• Strong SQL skills for querying, transforming, and analyzing large datasets.

Nice to Have

• Experience with Azure Machine Learning, MLflow, or similar MLOps platforms.
• Exposure to LLMs, GenAI, or AI agent workflows.
• Power BI or similar for communicating insights to stakeholders.
• Background in FP&A, demand planning, or a Global Business Services / Shared Services environment.
• Experience with ERP or financial consolidation systems (e.g., SAP, Oracle).
• Bachelor’s or Master's degree in a quantitative field (Computer Science, Statistics, Mathematics, AI, or related)