Senior Data Scientist, Product Data
Core
Own the analytical and technical foundation of product data quality across the ecosystem, spanning catalog hygiene, transaction matching, classification modeling, deduplication, and global product identity.
Role type
Senior IC data scientist (product data quality & entity resolution)
Builds
Scalable data pipelines, ML models for classification and matching, monitoring infrastructure, and product graph/retrieval systems
Domain
E-commerce / Marketplace / Product Data
Deliverable
production ML models | product features | dashboards & analysis
Required skills
Python, SQL, scikit-learn, XGBoost, LightGBM, PyTorch, TensorFlow, pandas, PySpark, entity resolution, fuzzy matching, clustering, embeddings, similarity-based techniques, data profiling, anomaly detection, statistics, ML theory
Preferred skills
vector search, embeddings, vector databases (FAISS, Pinecone, Weaviate), search/retrieval systems (Elasticsearch, Solr), graph databases (Neo4j), NLP techniques
Technologies
FAISS, Pinecone, Weaviate, Milvus, pgvector, Elasticsearch, Solr, Neo4j, BigQuery, NetworkX
Responsibilities
Develop and deploy ML models for automated product categorization and taxonomy assignment; Conduct deep-dive analyses into catalog completeness and consistency; Build and improve matching algorithms to link sales transactions to catalog products; Identify product variants and duplicates using clustering and entity resolution; Evaluate consistency of manufacturer-level attributes; Research and prototype improvements to product search and retrieval pipelines; Build and maintain dashboards and recurring reports for key product data KPIs; Take models and analytics prototypes from POC to production
Seniority
Senior, hands-on IC
