Data Scientist (P3109)

We are a community of data scientists that act as the voice of the customer – they share their story with us each and every day. Through simple, comprehensive, purposeful analytics, we fearlessly bring these customer stories and journeys to life. Our 360° customer view allows us to anticipate customer needs, thus enabling our clients to connect with their customers in meaningful, relevant ways.

We expect all data scientists to be hands-on with retailer databases and advanced analytics, but in this role you will additionally focus on applying machine learning, natural language processing, and modern AI frameworks to create scalable, intelligent customer solutions. 

RESPONSIBILITIES:

• Partner with senior data scientists and engineers to develop and test audience creation and recommendation solutions, including natural language–driven workflows.
• Query, clean, and transform large-scale customer datasets (loyalty, clickstream, digital interaction data) to support audience modeling and campaign targeting.
• Apply foundational statistics and machine learning techniques to measure customer behavior and campaign performance.
• Build and share insights and visualizations that translate technical findings into clear customer and business stories.
• Follow best practices for coding, quality assurance, version control, and documentation to ensure work can be scaled and reused.
• Actively participate in team discussions, retrospectives, and knowledge-sharing sessions to accelerate your learning and contribute to team success.
• Package building and code optimization experience or a strong desire to learn.
• Collaborate closely with teammates across product, engineering, and science to learn how solutions are scaled and operationalized.
• Challenging and improving 84.51° analytical capabilities/products.

QUALIFICATIONS, SKILLS, AND EXPERIENCE:

• Bachelor’s degree in a quantitative field (Statistics, Data Science, Computer Science or related discipline).
• Experience querying data from relational databases using SQL.
• Experience (academic projects, internships, or research) using R, Python, or other similar statistical software to develop analytical solutions.
• Exposure to data wrangling, cleaning, and dimensionality reduction techniques.
• Foundational understanding of machine learning concepts (classification, regression, clustering).
• Experience with (academic projects, internships, or research) Big Data concepts, tools, and architecture (e.g. Spark, Databricks, Pytorch).
• Strong communication skills, with the ability to explain technical ideas to non-technical audiences.
• Curiosity, adaptability, and a strong desire to learn from senior data scientists and cross-functional partners.
• Ability to work in a highly collaborative environment.

DESIRED

• Grocery and/or retail experience is a plus.
• Natural Language Processing (NLP) and Large Language Models (LLMs): Exposure to prompt engineering, intent extraction, or modern LLM APIs (OpenAI, Hugging Face).
• Schema and Taxonomy Design: Interest in defining structured data schemas and normalizing free-text for downstream modeling.
• Semantic Search & Embeddings: Familiarity with vector databases and embedding models for product/theme matching and retrieval.
• Evaluation Frameworks: Awareness of metrics like precision/recall, F1, and regression testing for model quality.
• Optimization & Recommender Systems: Understanding of how predictive propensities feed into recommendation workflows.
• Data-to-Insight UX Integration: Exposure to working with product/engineering teams on APIs or UI flows that surface AI-driven recommendations.
• Feedback Loop Design: Interest in methods for capturing user interactions and feeding them back into model improvement pipelines.

#LI-AB1