At Scribd (pronounced “scribbed”), we believe reading is more important than ever. Join our cast of characters as we work to change the way the world reads by building the world’s largest and most fascinating digital library: giving subscribers access to a growing collection of ebooks, audiobooks, magazines, documents, Scribd Originals, and more. In addition to works from major publishers and top authors, our community includes over 1.5M subscribers in nearly every country worldwide.

We’re defining the workforce of the future with Scribd Flex, a program that embraces multiple perspectives while leaning into our belief that no matter where each team member is, we trust them to accomplish our shared business goals. This program lets employees, in partnership with their manager, choose where they work while creating intentional in-person meetings with co-workers that build culture and connect us personally.

• The Applied Research - Personalization team’s goal is to model our users’ behavior by creating rich representations of their complex interactions with our content and delivering measurement and prediction models that drive ML product features. This is accomplished as a team of aligned, talented and collaborative data scientists that work to solve some of the company’s highest profile initiatives. Applied Research - Personalization is a new team and you will have a unique opportunity to shape our mission and initiatives.

• You are excited by the opportunities of working on Scribd’s unique and massive dataset consisting of hundreds of millions of documents, books, articles, audiobooks, and podcasts and the interaction of our content with millions of users.

• Understand how our users interact with the product to produce data and improve how user interactions create signals for ML models.

• Take full advantage of our scale of data by experimenting with cutting edge techniques in deep learning. For example, use Transformers and other architectures to extract rich user embeddings.

• Increase the effectiveness of personalization for new users by integrating sources of metadata and innovating on modeling techniques.

• Thoughtfully collaborate with other Data Scientists, Machine Learning Engineers, and System Engineers as well as our partners across the company.

• 2+ years of experience in data science, machine learning or related field.

• Bachelor's degree in a quantitative discipline. Master’s or Doctorate degree preferred.

• Interested or experience with ML personalization features and user modeling.

• Intermediate level or greater experience with Python. Experience with SQL and Spark is a plus.

• Experience with deep learning frameworks (such as TensorFlow or PyTorch) and embedding-based deep learning architectures is a plus.

• Healthcare Insurance Coverage: Scribd pays for employee’s Medical, Vision, and Dental premiums and a portion of dependent premiums

• 401k/RSP plans provided, plus company matching with no vesting period

• Professional development: generous annual budget for our employees to attend conferences, classes, and other events

• Quarterly Wellness, Connectivity & Comfort Benefit

• Concern mental health digital platform

• Free subscription to Scribd + gift memberships for friends & family

• Leaves: 12 weeks paid parental leave, company paid short-term/long-term disability plans and milestone Sabbaticals

• Generous Paid Time Off: Paid Holidays, Flexible Sick Time, Volunteer Day + office closure between Christmas Eve and New Years Day

• Company-wide Diversity, Equity, & Inclusion programs which include learning & development opportunities, employee resource groups, and hiring best practices.

Want to learn more? Check out our office and meet some of the team at www.linkedin.com/company/scribd/life