About the job
You will design, build, and optimize the recommendation systems that power Fortnite's Discover experience, serving personalized recommendations to one of the largest player bases in gaming across a massive catalog of creator-built experiences. You'll work across the full recommendation stack: candidate generation, content ranking, impression allocation, and real-time reranking.
Responsibilities
Design and implement retrieval, ranking, and reranking models for creator content using deep learning approaches (two-tower architectures, transformer-based sequence models, embedding-based retrieval) and build the user representation systems that power personalized discovery
Build and optimize multi-stage candidate generation and impression allocation pipelines that balance relevance, diversity, and fair content exposure across a large and rapidly evolving catalog
Design and run A/B experiments to validate model improvements, own evaluation frameworks that capture recommendation quality holistically, and drive the path from experiment to production deployment
Collaborate with analytics and content quality teams on ranking signals including genre classification, creator credibility, and content quality metrics
Own ML infrastructure decisions: choosing the right tradeoffs between batch, near-real-time, and streaming serving architectures
Qualifications
Minimum
5+ years of experience building production recommendation or ranking systems, ideally in a UGC, marketplace, or content discovery context
Experience with deep learning for information retrieval and multi-stage recommendation pipelines (candidate generation, scoring, reranking)
Demonstrated ability to design and analyze A/B experiments, with awareness of biases inherent to recommendation systems
Strong Python engineering skills with experience in PyTorch and large-scale data processing frameworks (Spark preferred)
Comfort working in a cloud-based ML environment
Experience with explore/exploit strategies, content cold-start, or counterfactual evaluation methods applied to recommendation
Experience with content understanding models (NLP, vision, or generative AI) used as ranking features
Familiarity with creator economy dynamics and how recommendation design affects content quality and creator incentives
Preferred
Experience with our stack: PyTorch (TorchRec, Transformers), Ray, Databricks, AWS
Passion for video games and/or experience with gaming analytics