About the job
84.51° Overview:
At 84.51°, we are at the forefront of retail data science, insights, and media. We collaborate with The Kroger Co., consumer packaged goods organizations, agencies, publishers, and affiliates to deliver personalized and valuable shopping experiences throughout the purchasing journey.
Leveraging advanced science, we utilize first-party retail data from over 62 million U.S. households through the Kroger Plus loyalty card program to enhance customer-centric journeys with 84.51° Insights, 84.51° Loyalty Marketing, and our retail media advertising solution, Kroger Precision Marketing.
We embrace a 5-day in-office work schedule to foster collaboration, alignment, and team connectivity.
Join us in making a difference at 84.51°!
__________________________________________________________
Senior ML Data Engineer, Relevancy Sciences – Personalization & Loyalty Strategy (P508)
The Relevancy Sciences Team is dedicated to crafting relevant and personalized customer experiences for Kroger's E-commerce platform, recognized as one of the top 10 e-commerce companies in the U.S. We generate trillions of recommendations daily and deliver them to millions of Kroger customers. Our team manages an extensive portfolio of machine learning solutions for search and product recommendations. We are on the lookout for a skilled and experienced Senior ML Data Engineer to join our data science team, specializing in developing search and recommender systems.
Role Overview
In this role, you will design, build, and maintain the crucial data infrastructure that powers our machine learning models, encompassing everything from feature engineering to training data generation. You will act as a liaison between ML requirements and production data systems, overseeing feature stores, training/evaluation pipelines, and ML-specific data operations. Your efforts will empower data scientists to iterate swiftly while ensuring production-grade reliability and scalability.
What You'll Do
- Feature Store Operations & Governance (40%)
- Manage the lifecycle of feature requests from intake to deployment, promoting reusability and maintaining a searchable feature catalog.
- Design and develop scalable feature pipelines that compute features from various sources (BigQuery, Azure Data Lake) and integrate them into the Feature Store infrastructure (Vertex AI Feature Store + BigQuery).
- Create streaming feature engineering pipelines utilizing Apache Beam/Dataflow for real-time feature computation and low-latency model serving.