Data Scientist -Marketing & Customer Insights

Data Science & Analytics at Casey’s is a centralized group that partners with various business units including merchandising, store operations, fuel (supply, transportation, and pricing), and supply chain, to deliver insightful, practical, and effective solutions to help business make crucial data-driven decisions to maximize ROI and company’s brand equity. The selected candidate will have the opportunity to be part of a highly skilled and cross-functional team to deliver strategic solutions using AI/ML, technology, and analytical methods.

In this role you will lead and own all data science initiatives in the marketing and customer insights space. You will have the opportunity to work on some of the challenging problems, unique to the C-Store retail space, and build ML models using cutting-edge technologies to deliver high-impact solutions. You will work closely with a team of talented data scientists, product owners, data engineers, and other technology leaders. This position is based in Ankeny, Iowa, and you will be reporting to the Director of Data Science & Analytics.

• Open to hiring at multiple levels based on skills & experience.
• Open to H1B Visa Transfers, sorry no student visa's at this time.
• Prefer candidates who are willing to relocate to Iowa, if outside of Iowa qualified candidate must reside within Casey's 17 state footprint.

Responsibilities:

• Partner with stakeholders in marketing and customer insights business units to translate and formulate complex business problems into appropriate data models using a range of statistical and AI/ML methodologies, experiment with various approaches, implement models into production using cloud technologies, and communicate the insights to business. Comfortable working in a fast-paced agile environment.
• Develop & build accurate marketing measurement and attribution capabilities, customer behavioral patterns and personalization. You will lead the development and delivery of data science solutions that help us understand our customers better, design and measure incremental value in marketing campaigns to maximize customer satisfaction and strengthen the company’s brand.
• Follow established state-of-the-art MLOps practices in a Cloud setting (preferably Azure) to scale the models in production.
• Work on data science and AI/ML projects in other areas in supply chain as well, if needed.
• Work with data analysts to design insightful dashboard and reports as needed.
• Mentor junior data scientists

Requirements:

• Master’s or PhD degree in statistics, econometrics, operations research, engineering, or related field; Bachelor’s degree in a quantitative field with extensive relevant industry experience.
• 5 years of industry experience in data science / ML preferably at a retail company in marketing or customer analytics including market mix modeling, attribution, customer lifetime modeling, propensity and churn modeling, segmentation etc.
• Strong programming experience with Python and/or R.
• Demonstrable experience in writing advanced SQL.
• Experience with data science and ML packages/technologies like scikit-learn, AutoML; Bonus: TensorFlow, PySpark, ML tools on Azure/Databricks.
• Proficiency in statistics and ML – hypothesis testing, regression incl causal inference, classification, tree-based models, neural networks, unsupervised learning, text analysis, recommender systems etc.
• Experience in end-to-end model building and deployment to production on cloud environments using MLOps practices.
• Experience in data story-telling using compelling visualizations and ability of explain complex data concepts in simple language.
• Passion to experiment with out-of-the-box approaches and have courage to fail fast

Preferred Skills/Abilities:

• Prior experience with digital and retail media advertising tools.
• In-depth knowledge and practice of software engineering principles, best coding practices etc., in a agile setup.
• In-depth knowledge of data analytic cloud platforms, databases, and surrounding ecosystems (Azure or Databricks Preferred), and Source Control & Documentation Tools. Examples include GitHub, Teams, and Confluence.
• Proven ability to thrive in and work with noisy and ambiguous data in a fast-paced environment with tight deadlines.
• Proven ability to write high-quality code that is scalable, efficient, readable, and bug-free.
• Excellent interpersonal, verbal and written communication skills.
• Excellent interpersonal, verbal and written communication skills with the ability to convey complex data-driven insights to non-technical stakeholders.
• Must be detail oriented with strong attention to accuracy.
• Excellent analytical and hardworking problem-solving mindset.
• Excellent problem-solving skills with the ability to influence team members at different levels.