Senior Machine Learning Engineer, Discovery Recommendations

Epic Games • Cary, NC

2d

About The Position

Design, build, and optimize the recommendation systems powering Fortnite’s Discover experience, delivering personalized recommendations across a large player base and a massive catalog of creator-built experiences. The role spans the full recommendation stack, including candidate generation, content ranking, impression allocation, and real-time reranking, in a rapidly changing content environment where new experiences are published daily and quality signals may be sparse.

The engineer will develop retrieval, ranking, and reranking models and user representation systems; build multi-stage recommendation and impression allocation pipelines; design and analyze A/B experiments; and move validated improvements into production. The role also involves collaborating with analytics and content quality teams, and making ML infrastructure decisions across batch, near-real-time, and streaming serving architectures.

Requirements

• At least 5 years of experience building production recommendation or ranking systems.
• Experience with deep learning for information retrieval and multi-stage recommendation pipelines, including candidate generation, scoring, and reranking.
• Demonstrated ability to design and analyze A/B experiments, with awareness of biases inherent to recommendation systems.
• Strong Python engineering skills.
• Experience with PyTorch and large-scale data processing frameworks; Spark is preferred.
• Comfort working in a cloud-based ML environment.
• Experience with the listed stack: PyTorch (TorchRec, Transformers), Ray, Databricks, and AWS.

Nice To Haves

• Recommendation or ranking experience in a user-generated-content, marketplace, or content discovery context.
• Experience with explore/exploit strategies, content cold-start, or counterfactual evaluation methods applied to recommendation.
• Experience with content understanding models, such as NLP, vision, or generative AI, used as ranking features.
• Familiarity with creator economy dynamics and how recommendation design affects content quality and creator incentives.
• Passion for video games and/or experience with gaming analytics.

Responsibilities

• Design and implement retrieval, ranking, and reranking models for creator content using deep learning approaches, including two-tower architectures, transformer-based sequence models, and embedding-based retrieval.
• Build user representation systems for personalized discovery.
• Build and optimize multi-stage candidate generation and impression allocation pipelines that balance relevance, diversity, and fair content exposure across a large, 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, including tradeoffs among batch, near-real-time, and streaming serving architectures.

Benefits

• The company pays 100% of medical, dental, vision HRA, long-term disability, life insurance, and 401(k) premiums for employees and dependents.
• 401(k) with competitive match.
• Mental well-being program through Modern Health, including free therapy and coaching for employees and dependents.
• Company events and company-wide paid breaks.
• Unlimited PTO and sick time.
• Paid sabbatical in recognition of 7 years of employment.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed