Data Scientist

Job Title: Data Scientist – eCommerce Search Location: St. Louis, MO Job Summary We are seeking a Data Scientist – eCommerce Search to help enhance and optimize the search experience for a global eCommerce platform. In this role, you will design and implement machine learning models, improve search relevance, develop semantic search capabilities, and optimize search engine performance. You will collaborate with product owners, data scientists, and software engineers to deliver intelligent, personalized search experiences that improve product discovery and customer engagement. Key Responsibilities • Design, train, and optimize machine learning models for search relevance and personalized ranking. • Build and improve learning-to-rank, neural ranking, and embedding-based search models. • Analyze search query logs and user behavior to improve search accuracy and relevance. • Develop feature engineering pipelines using search, product, and customer data. • Implement semantic search using NLP, embeddings, and dense retrieval techniques. • Tune Elasticsearch, OpenSearch, Solr, or Lucene configurations, including BM25, tokenization, stemming, and query parsing. • Build and maintain end-to-end ML pipelines using MLOps best practices. • Develop personalized ranking strategies based on user intent and business goals. • Monitor production search performance, identify model drift, and continuously improve search quality. • Collaborate with cross-functional teams to deliver scalable and high-performing search solutions. Required Qualifications • Bachelor's degree in Computer Science, Data Science, Engineering, or a related quantitative field. • 3+ years of experience in Machine Learning, Data Science, Search Relevance, or Ranking Systems. • Strong programming experience with Python. • Hands-on experience with ML frameworks such as Scikit-learn, TensorFlow, PyTorch, or MLFlow. • Experience with feature engineering, model training, and data preprocessing. • Strong knowledge of SQL and working with large datasets using Pandas, NumPy, and Spark. • Experience building ranking models such as Learning-to-Rank (LTR) or neural ranking models. • Hands-on experience with semantic search, embeddings, or dense retrieval techniques. • Strong understanding of search technologies including Elasticsearch, OpenSearch, Solr, or Lucene. • Experience with search relevance tuning, BM25, tokenization, stemming, query parsing, and information retrieval concepts. • Familiarity with MLOps practices including model versioning, experiment tracking, and pipeline orchestration. • Excellent analytical, problem-solving, and communication skills. Preferred Qualifications • Experience analyzing search query logs and search performance metrics. • Experience training and fine-tuning machine learning models. • Knowledge of Large Language Models (LLMs) and prompt engineering. • Experience with vector search, semantic indexing, and vector databases. • Familiarity with search analytics and dashboards. • Experience with Tableau, Looker, or similar visualization tools. • Background in NLP, Information Retrieval, or Computational Linguistics. • Experience working on search-focused or machine learning product teams. Nice to Have • Experience with eCommerce search or product discovery platforms. • Knowledge of recommendation systems and personalized search. • Experience with microservices, event-driven architectures, and CI/CD pipelines.