Senior Machine Learning Engineer, Premium Discovery at Scribd in San Francisco, CA

Job description

Scribd, Inc. is on a mission to advance human understanding. Our four products — Scribd®, Slideshare®, Everand™, and Fable — help billions of people across the globe move beyond access and into insight, application, and expertise. Culture at Scribd, Inc. We support a culture where our employees can be real and be bold; where we debate and commit as we embrace plot twists; and where every employee is empowered to take action as we prioritize the customer. We believe the best work happens when individual flexibility is balanced with meaningful community connection. Scribd Flex empowers employees to choose the workstyle and location that support their best performance, while committing to intentional in-person moments that strengthen collaboration and culture. Occasional in-person attendance is required for all Scribd, Inc. employees, regardless of location. So what are we looking for in new team members? At Scribd, Inc., we hire for “GRIT.” Traditionally defined as the intersection of passion and perseverance toward long-term goals, GRIT reflects the mindset we expect from every employee. For us, it also serves as a practical framework for how we work: setting and achieving Goals, delivering Results within your role, contributing Innovative ideas and solutions, and strengthening the broader Team through collaboration and attitude. This posting reflects an approved, open position within the organization. About the team Premium is the Scribd Inc. pillar behind two reading products: Everand, the audiobook and ebook subscription app, and Fable, the social app where readers track, discuss and discover books. Helping readers find their next book is central to both, so search and recommendations sit at the heart of the products. You'll join Premium's new Discovery squad. It's a small, dedicated group of recommendations, search, applied research and ML engineers working full time on discovery for Everand and Fable. The squad works closely with Orion, Scribd's ML platform team. Orion runs the feature store, model registry, embedding-based retrieval and model serving behind discovery across Scribd, Slideshare and Everand. Role overview We're looking for a Senior Machine Learning Engineer to own recommendations for Fable and grow into the technical lead for Premium recommendations. Fable's recommender today is a collaborative-filtering model built in house. It has served readers well, but it has no real-time signals and no learned ranking, and it can't recommend to new or lapsed readers. Your first big project is to move Fable onto Orion, so Fable and Everand share a modern recommendation stack. Key responsibilities • Lead the migration of Fable's recommendations onto Orion, covering data, features, training, serving and experiments, while keeping today's recommendations running. • Extend Orion's rankers, feature store and embedding-based retrieval to support Fable, in partnership with the Orion ML platform team. • Own the health of Fable's recommendation systems in production: quality, latency, cost and on-call. • Bring Fable's social signals (shelves, ratings, reviews, book clubs, reader similarity) into recommendations for both Fable and Everand. • Design and analyze A/B tests with product managers and analysts to decide what ships. • Act as technical lead for Premium recommendations. Shape the roadmap with product managers, and see work that depends on other teams' systems through to delivery. • Raise the bar on engineering practice in the squad through design reviews, code quality and operational readiness. Tech you'll work with You'll work across two stacks: Fable's on Google Cloud and Orion's on AWS. • Fable: Python (FastAPI, Django), PostgreSQL, BigQuery, Kubernetes, Google Cloud including Vertex AI • Orion and Everand: Python, Go and gRPC, Ruby on Rails, Databricks and Spark, Airflow, AWS SageMaker, Weaviate for embedding-based retrieval, feature store and model registry • Infrastructure: AWS (EKS, ECS, Lambda, SQS, ElastiCache),