Senior Data Scientist
The Marketing Data Science team at Wayfair develops machine learning models and reinforcement learning systems to power algorithmic decision-making across paid and owned media and marketing channels, including Paid Search, Display & Social Ads, Direct Mail, Email Marketing and Push Notifications.
In this role, you will leverage massive amounts of data to solve complex business problems focused on enhancing the customer experience and driving long-term value. You will be processing petabytes of first party and third party clickstream data to build customer-centric ML models. These models ultimately plug into our ecosystem of algorithmic decision-optimization systems and power millions customer-level decisions each day. Depending on your specific pod, these predictions or decisions could range from: What do we think she needs? What’s her stylistic preference? Should we show her an ad? On what channels? How frequently? How much do we bid? Which creative asset speaks to her uniqueness? etc.
Above all, you’ll get to work on problems that are both intellectually-challenging and drive real, measurable impact, first and foremost, for our customers - and as a result for Wayfair at large. To get a better sense of the type of projects we actually work on, check out our Data Science & Machine Learning blog posts here!
What You'll Do
- Own the full data science lifecycle for your portfolio of problems - from conception to prototyping, testing, deploying, and measuring its overall business value
- Train deep-learning models for prediction tasks as well as representation learning.
- Partner closely with peer data scientists and ML engineers from our Search and Recommendations team, and from other partner engineering teams, to deploy and integrate our model outputs into existing production systems.
- Develop quantitative models and decision-optimization systems by leveraging big data technologies, machine learning algorithms, and sound data analysis
- Wrangle and process petabytes of data from various data sources
What You'll Need
- PhD in quantitative field (e.g. PhD in mathematics, computer science, engineering, operations research, physics, economics, etc.) and/or BSc/MS + 1-2 years of experience as a data scientist
- Strong grasp of ML foundations (supervised learning, bias/variance trade-off) and strong interest in deep learning and experience with basic neural network architectures
- Proficient at one or more programming languages, e.g. Python, R, Java, C++, etc.
- Comfortable with SQL and ability to wrangle data from various sources
- While prior experience with big data technologies is not necessary (Hadoop, Hive, Spark), having a desire to learn such tools is something we look for
- Ability to effectively work with non-technical stakeholders: strong communication skills, ability to synthesize conclusions and desire to influence business decisions
- Action-oriented, autonomous individual with a bias towards solving problems from a customer-centric lens
- A knack for finding the right degree of pragmatism and delivering solutions in a iterative manner, adding only as much complexity as needed in each step along the way
- A curious mind open to continuous learning and motivated to autonomously drive projects and thrive in a dynamic environment where there can be ambiguity