Data Scientist

Remote Duration: 12 months In this pivotal role, you’ll enable targeted marketing, customer engagement, and data-driven commercial strategies through robust segmentation, predictive modeling, and campaign analytics. You’ll also play a key role in deploying, automating, and maintaining production-grade analytics solutions using modern MLOps practices. What You’ll Do Customer Segmentation • Build and maintain flexible, multi-level customer segmentation frameworks using clustering and advanced feature engineering, enabling differentiated marketing and sales strategies. Propensity And Predictive Modeling • Develop models to predict customer behaviors such as likelihood to purchase, respond to campaigns, or churn, empowering teams to focus resources where they’ll have the greatest impact. Customer Value Analysis • Estimate and analyze customer lifetime value (CLV) and identify high-potential and at-risk customers to inform retention and growth initiatives. Campaign Measurement & Uplift Modeling • Evaluate the effectiveness of marketing campaigns and interventions, using uplift modeling and other techniques to optimize spend and strategy. Next-Best-Action/Product Recommendations • Deliver insights and tools that recommend the most relevant product, service, or engagement for each customer segment. Model Deployment & Productionization • Deploy predictive models and analytics solutions into production environments, ensuring reliability, scalability, and maintainability. Automation & Monitoring • Build and maintain automated pipelines for model training, deployment, and monitoring, enabling continuous improvement and reliability of analytics solutions. Code Review & Collaboration • Participate in code reviews (PRs) and collaborate with engineering teams to ensure code quality, reproducibility, and adherence to best practices. Stakeholder Engagement • Partner with commercial, marketing, and product teams to identify analytics needs, deliver impactful solutions, and provide training and documentation for end users. What You’ll Need Education • Bachelor’s degree (Master’s preferred) in a quantitative field such as Econometrics, Statistics, Marketing Science, Business Analytics, Quantitative Marketing, Applied Mathematics, or a related discipline. • Master’s degree or higher in any of the above fields, or equivalent professional experience demonstrating advanced technical and business analytics skills. Experience • 7+ years of hands-on experience in customer analytics, segmentation, or predictive modeling within a commercial, marketing, or customer-focused environment. • Proven track record of delivering analytics that drive business decisions and measurable outcomes. Technical Skills • Advanced proficiency in Python (pandas, scikit-learn, PySpark, SQL functions) and experience with Spark for large-scale data processing. • Demonstrated experience with clustering, propensity modeling, uplift modeling, and customer value analysis. • Strong background in feature engineering, data enrichment, and data quality management. • Experience with MLOps tools and practices (e.g., MLflow, Kubeflow, Airflow, Docker, Kubernetes) for model deployment, monitoring, and lifecycle management. • Proficiency with version control (Git) and CI/CD pipelines for automating analytics workflows. • Experience deploying models and analytics solutions to cloud platforms (Azure, AWS, GCP) and monitoring their performance in production. Business & Communication Skills • Ability to translate complex analytics into clear, actionable insights for commercial and marketing stakeholders. • Experience working cross-functionally with business teams to identify needs, deliver solutions, and drive adoption. • Excellent written and verbal communication skills, including documentation and training for non-technical users. • Strong problem-solving skills, business curiosity, and a results-driven mindset. Preferred Qualifications • Experience in commercial analytics, marketing analytics, or customer analytics roles within agriculture, retail, CPG, or other B2B industries with complex customer relationships. • Familiarity with causal inference in observational studies, next-best-action modeling, and customer journey analytics. • Experience building self-service analytics tools or utilities for business teams. • Knowledge of data governance best practices and experience supporting data-driven business transformation. • Knowledge of MLOps best practices for deploying and managing production models, including monitoring, versioning, and automation. • Experience with containerization (Docker, Kubernetes) and orchestration tools for scalable analytics operations. • Experience participating in code reviews and collaborative development processes. • Familiarity with building automated pipelines for model training, deployment, and monitoring. • Proficiency with PySpark for large-scale data processing.