Lead Data Scientist - Relevancy Sciences (P3764)

Lead Data Scientist - Relevancy Sciences

Relevancy Sciences Team is responsible for powering relevant, personalized, and scalable customer experiences across Kroger’s e-commerce ecosystem. We build and evolve the science behind search and recommendations that serve millions of customers and support high-scale digital experiences.

We are seeking a Lead Data Scientist to provide technical leadership across search and recommender systems, with a strong focus on modern model architectures, and production-ready machine learning. This role is ideal for someone who combines depth in applied machine learning with strong systems thinking, cross-functional influence, and contributes towards agentic capabilities.

Responsibilities:
Technical Leadership, Ownership, and Influence. Own and drive technical initiatives across search & recommender systems. Define and evolve the science strategy for improving content discovery, relevance, personalization, and decision support across digital experiences. Identify high-impact opportunities, make clear technical tradeoffs, and guide the team towards scalable, practical solutions. Rapidly prototype and validate new ideas to accelerate adoption and demonstrate measurable value.

Develop innovative search & recommender systems. Design and build ML solutions tailored to the unique needs of grocery retail domain. Lead the development of systems that improve product discovery and personalization across customer journeys. Bring strong technical and thought leadership on next generation personalization, including the use of Generative AI and agent-based approaches.

Evaluate and improve ML performance. Establish rigorous evaluation methodologies to assess the performance of ML systems across key metrics. Define robust online evaluation frameworks, and guide experimentation strategies that connect model improvements to customer and business outcomes.

Model serving and deployment. Partner closely with Engineering to build and deploy production-ready ML systems. Influence design decisions related to real-time inference, feature access, system integration, monitoring, and reliability. Ensure solutions meet latency, scalability, and operational requirements. Contribute to the evolution of serving and deployment strategies.

Cross-functional leadership. Work closely with Product, Engineering, and business stakeholders to translate needs into clear problem statements, hypotheses, and execution plans. Drive alignment across teams and influence decisions through clear communication of tradeoffs, risks, and expected outcomes.

Mentoring and knowledge sharing. Mentor data scientists and lead technical reviews to improve model quality, experimentation rigor, and systems thinking. Promote best practices in reproducibility and evaluation. Contribute to building a strong, learning-oriented team culture.

Requirements:
Bachelor’s, Master’s, or PhD in Computer Science, Data Science, Statistics, Mathematics, Engineering, or a related quantitative field.
6+ years applied ML with explicit search and/or recommendation systems experience.
Demonstrated experience designing and building systems at scale — including representation learning, candidate retrieval and ranking with multi-stage pipelines
Proficient in Python and SQL, with experience processing large-scale data in distributed environments (e.g., Spark).
Track record of shipping ML systems that moved business or customer metrics at scale – not just exposure to frameworks or techniques.
Strong foundation in statistics, experimentation, and data analysis, including design of experiments and A/B testing.
Hands-on experience building or rigorously evaluating LLM- and agent-based systems (e.g., RAG, agentic workflows, LLM-based evaluation), with clear judgment on where these techniques apply and where they don't.
Experience partnering with engineering teams to deploy and maintain machine learning systems in production.
Understanding of real-time systems, model serving, feature pipelines, and monitoring.
Ability to make practical tradeoffs between model complexity, performance, latency, and scalability.
Demonstrated ability to lead technical work across projects and influence direction across data science, engineering, and product teams.
Experience mentoring or guiding other data scientists and contributing to a strong technical culture.
Experience working with cloud platforms such as GCP or Azure.
Experience in retail, e-commerce, or high-scale consumer domains is a plus.

Why join our team? (Rewards)
Impact millions of people. As a member of our data science team, you will have the opportunity to make a tangible difference in the lives of millions of customers by delivering relevant and personalized recommendations that enhance their grocery shopping experience. Your work will directly contribute to increasing customer satisfaction and loyalty, driving business outcomes for our company.
Continuous learning and development. Challenge yourself. We are committed to fostering a culture of continuous learning and development. You will have access to resources and support for expanding your knowledge and skills in cutting-edge technologies, including recommender systems, machine learning and artificial intelligence. Our team encourages exploration and experimentation, providing opportunities to stay at the forefront of industry advancements.
Work on new developments in search & recommender systems. Join a team at the forefront of innovation in search, recommender systems and AI. You will have the chance to contribute to pushing the boundaries of what’s possible in personalized recommendation technology. You will have the chance to work on exciting projects that leverage the latest developments in deep learning architectures and data science methodologies.

#LI-SSS