Staff Data Scientist

Staff Data Scientist

We are looking for a data scientist to build and deploy models that help drive the sales of sports apparel for your favorite teams. This position is on the commerce customer marketing science group--they create the machine learning models to help get customers to the products they want. An example project is taking tens of millions of customers and predicting their team preferences using past behavior and sports seasonality. Another example is model which customers are likely to make a repeat purchase. This is a high impact role within the company due to the vast amount of marketing spend in the organization.

A staff level data scientist is considered a technical lead role. They will be leading an entire data science workstream. They will take a business objective (like improve our marketing personalization) and figure out how to turn it into a data science problem. At that point they will choose the methodology and how to implement it. They also may be leading other data scientists as part of the work, and mentoring data scientists more broadly.

What you'll do:

• Train machine learning models for customer marketing (CRM) purposes
• Deploy models into production to run at scale
• Use exploratory analysis to understand how business problems can be modeled
• Communicate across the company to align business goals with science techniques and report results outwards
• Determining how to turn business problems into data science projects and how to solve them
• Lead data science projects end-to-end
• Mentor junior employees in data science techniques and approaches

The ideal candidate would have:

• At least 5 years of experience as a data scientist or machine learning engineer specifically
• At least one example of having mentored a junior data scientist or machine learning engineer
• The ability to write code in Python, R, or other data science languages
• An understanding of marketing science use cases (customer segmentation, lifetime value models, etc.)
• Experience with data science modeling techniques such as XGBoost, regressions, hyper-parameter tuning, and feature selection
• At least one past instance of having a model run continuously in production (like as an API or an automated batch process)
• A history of past positions where complex business goals were converted into data science problems
• Experience with using large and complex datasets spanning many tables
• Experience with running data science tasks in managed cloud environments (AWS, GCP, Azure)