Machine Learning Scientist

Who we are

Wayfair is moving the world so that anyone can live in a home they love – a journey enabled by more than 3,000 Wayfair technologists. Our Scientists build state-of-the-art algorithms to power the varied & broad spectrum of challenges in the Wayfair marketplace; from empowering suppliers to easily add products to our catalog, to enabling our customers to discover and purchase a vast & diverse assortment of home goods, to driving marketing experiences customers love all at web scale. 

The Search ML team is responsible for the algorithms that power Wayfair’s global search experience across all countries and stores as well as all other recommendation services at Wayfair (item-to-item, browse, email, etc.) for both our core e-shopping experience and brand-based content. Using state-of-the-art web-scale machine learning, including cutting-edge NLP, deep-learning models, and multi-modal technology, these teams power a fundamental set of experiences for our over 22 million active customers. Our mission is to help our customers determine their style and needs efficiently, delivering an end-to-end personalized and inspiring experience.

In support of that mission, we are looking for machine-learning scientists with deep domain expertise and practical experience in at least one of the following: NLP & Natural Language Understanding, Deep Learning & Transformer architectures, or Search & Information Retrieval. In this role, you’ll partner with fellow scientists, engineers, analysts, and product managers to apply science and machine learning skills to directly impact Wayfair’s customers, revenue, and profitability. 

What you’ll do

• Design, build, deploy and refine large-scale machine learning models and algorithmic decision-making systems that solve real-world problems for customers.
• Work cross-functionally with commercial stakeholders across product and analytics to understand business problems or opportunities and develop appropriately scoped analytical solutions.
• Collaborate closely with various engineering, infrastructure, and ML platform teams to ensure adoption of best-practices in how we build and deploy scalable ML services.
• Identify new opportunities and insights from the data (where can the models be improved? what is the projected ROI of a proposed modification?)
• Be obsessed with the customer and maintain a customer-centric lens in how we frame, approach, and ultimately solve every problem we work on.
• Foster the development of junior ML scientists on the team through mentorship and knowledge-sharing.

What you’ll need

• Bachelor’s or Master’s degree in Computer Science, Mathematics, Statistics, or related field.  
• 5-7 years of industry experience in developing machine learning algorithms and deploying them into production at web scale.
• Proficiency in Python or one other high-level programming language.
• Familiarity with productionized code bases and PRs; comfort mentoring junior scientists to improve their code quality.
• Concrete hands-on expertise deploying machine learning solutions into production.

• Theoretical understanding of statistical models such as regression, clustering and ML algorithms such as decision trees, neural networks, etc. 
• Deep domain knowledge of at least one of: NLP & Natural Language Understanding, Deep Learning & Transformer architectures (including frameworks such as PyTorch, Tensorflow, etc.), or Search & Information Retrieval.

• Strong written and verbal communication skills, ability to synthesize conclusions for non-experts, and overall bias towards simplicity. 
• Intellectual curiosity and enthusiasm for continuous learning.

Nice to have

• Ph.D. in a quantitative field with a track record of relevant publications
• Experience with Python ML ecosystem (numpy, pandas, sklearn, XGBoost, etc.)
• Familiarity with cloud ML tooling: GCP (or AWS, Azure), ML model development frameworks, ML orchestration tools (Airflow, Kubeflow or MLFlow)
• Expertise or practical experience across information retrieval, query/intent understanding, search ranking, recommender systems, etc.