Data Scientist, Forecasting
Pinterest, San Francisco, CA, US; Seattle, WA, US
Visual discovery destination
Millions of people across the world come to Pinterest to find new ideas every day. It’s where they get inspiration, dream about new possibilities and plan for what matters most. Our mission is to help those people find their inspiration and create a life they love. In your role, you’ll be challenged to take on work that upholds this mission and pushes Pinterest forward. You’ll grow as a person and leader in your field, all the while helping Pinners make their lives better in the positive corner of the internet.
We’re looking for a data scientist to help us forecast Pinterest’s most critical metrics, from user growth to revenue. You will work closely with product, data science and business groups to understand and model both the underlying mechanics of the business, and the effect of exogenous factors. The ideal candidate will possess both strong technical and communication skills; able to explain complex models to leadership in product, engineering, and business teams.
The output of your models will provide context for product and business performance management and serve as an input into the company's top-line goals. You will also contribute to internal forecast tooling, methods, and infrastructure.
What you’ll do:
- Progressively translate components of Pinterest’s business-model into time-series ML models
- Work with stakeholders to understand the mechanics of the business, risks, and opportunities
- Creatively apply forecasting methods to represent the dynamics of the business
- Develop a deep understanding of how forecast outputs are expected to behave, present results, and offer guidance
- Closely partner with product, finance, and engineering teams to put your solutions into practice and to re-engineer existing processes
- Create, maintain, and own model-deployment and data pipelines
- Contribute to internal forecasting methods, tooling, and infrastructure
What we’re looking for:
- 5+ years of industry experience with proven ability to apply scientific methods to solve real-world problems on web-scale data
- Experience of time-series forecasting; model creation, evaluation, selection, and communication
- Experience with one or more low-level probabilistic/ML frameworks (e.g. Stan, Pyro, PyTorch, Tensorflow)
- Expert in at least one scripting language (Python/R)
- Proven ability to create and maintain big data pipelines
Pinterest is full of possibilities to design your life. Discover recipes, style inspiration, projects for your home and other ideas to try.
Want to learn more about Pinterest? Visit Pinterest's website.
Innovative, fast-paced, challenging.. we're everything you want in a workplace.