Java Programming, Python Programming, SQL, Data science techniques
This is a leadership position in an applied science role to develop foundational capabilities for Wayfair:
1) Understanding the relationship between product information across text and image modalities: product-content similarity
2) Predict product substitutability before a product enters our catalog: day zero substitutability
3) Build feedback loops from our customers to discover and exploit substitution in our catalog: marketplace substitutability
Optimizing these capabilities for the complexity of information about our products, the breadth and diversity of our catalog, in a way that supports Wayfair's global growth, pose key challenges. Further, product substitutability is difficult and potentially costly to measure as our products are not commodity goods that are repeatedly purchased (e.g. the customer needs the perfect sofa for their living room). We build generalized, unified models in the form of rich, concise representations to address these challenges and power decision making across Wayfair. These are used as i) features for other science models predicting customer engagement with our products, ii) through scalable search systems for discovering exact or substitutes across our catalog or our competitors', and iii) validation of substitution to drive end-to-end efficiency in product sourcing, on-site recommendations, and distribution.
What You’ll Do
Wayfair Inc. is an American e-commerce company that sells furniture and home-goods. Formerly known as CSN Stores, the company was founded in 2002. Their digital platform offers 14 million items from more than 11,000 global suppliers. The online company is headquartered in Boston, Massachusetts, Wayfair has offices and warehouses throughout the United States as well as in Canada, Germany, Ireland, and the United Kingdom.
Berlin, Germany
0-2 year