Sr Applied Data Scientist - Search and Browse (Applied ML, NLP, LLMs)

Target•Brooklyn Park, MN

11d•$98,000 - $211,000•Hybrid

About The Position

The Applied Data Sciences team at Target focuses on developing and managing state-of-the-art predictive algorithms that leverage data at scale to automate and optimize decisions. This role is within the Search and Browse Applied Data Science team, which builds the core relevance, retrieval, ranking, and personalization systems for Target's Digital experience. The team develops scalable ML systems to enhance product discovery, semantic search, browse relevance, and customer engagement across mobile and web platforms. They are working on next-generation discovery experiences using advancements in LLMs, semantic retrieval, and conversational AI to help millions of guests find products quickly and intuitively within large, dynamic retail catalogs. The team tackles large-scale search challenges, including natural language and long-tail search, semantic retrieval, zero-shot item understanding, and AI-native commerce discovery experiences operating at high query per second (QPS) with strict latency and reliability requirements.

Requirements

PhD or MS in Computer Science, Statistics, Applied Mathematics, Physics or related quantitative discipline.
3+ years of industry experience in Machine Learning, Data Science, Search, NLP, Personalization or related ML systems.
Exceptional experience with retrieval/ranking systems, semantic search, NLP, vector search, or related ML domains.
Strong coding skills in Python and SQL with experience in distributed data processing ecosystems.
Demonstrated hands-on experience building and deploying production ML systems at scale.
Strong understanding of production ML system tradeoffs including latency, scalability, reliability, and operational excellence.
Experience with modern ML approaches such as embeddings, transformers, semantic retrieval, RAG systems, or GenAI technologies.
Experience designing experiments and interpreting online/offline metrics.
Strong problem-solving skills with the ability to independently drive projects in moderately ambiguous environments.
Very good communication and cross-functional collaboration skills.
Constant learner mentality who stays current with new and evolving AI technologies via formal training and self-directed education.

Responsibilities

Develop and deploy scalable ML models for search ranking, browse personalization, semantic retrieval, and query understanding systems.
Design and execute offline and online experiments to improve relevance, engagement, conversion, and customer satisfaction.
Build scalable feature pipelines, evaluation frameworks, and ML workflows for production systems.
Apply modern ML techniques including embeddings, retrieval/ranking models, transformers, NLP, vector search, and GenAI/RAG systems.
Improve query understanding, catalog understanding, semantic retrieval, and long-tail search relevance across large retail catalogs.
Partner closely with Product, Engineering, and Infrastructure teams to align technical solutions with business priorities and operational requirements.
Drive data-informed decision making through deep analysis, experimentation, and business impact measurement.
Balance model quality with latency, scalability, reliability, and infrastructure efficiency in large-scale production systems.
Contribute to best practices in experimentation, ML engineering, and operational excellence.
Mentor junior scientists and collaborate across teams to improve Search and Browse experiences.