Recommendation Systems are a key growth lever at Roblox, driving retention, engagement, and monetization for hundreds of millions of users. This role offers the unique opportunity to redefine how users search and discover everything from the most interesting immersive experiences and digital avatars in our Marketplace to personalized advertising. You will solve a diverse range of high-scale ranking, retrieval, and personalization problems across our platform.

We combine cutting-edge research —including deep learning, generative AI, and reinforcement learning techniques— with large-scale engineering to bridge experimentation and production; you'll design algorithms that operate at massive scale and shape the next generation of recommender systems for  user-generated content.

Teams Hiring for This Role

• Discovery: powers major search and recommendation surfaces—drives user engagement by redesigning core surfaces and search/homepage ranking
• Economy: builds the ML backbone for marketplace, monetization, and commerce (including fraud, pricing, and bundling) 
• Ads & Brands: focuses on ranking, retrieval, and marketplace/auction theory to optimize sponsored content delivery.

You Will

• Design and implement large-scale recommendation systems that power discovery across Roblox’s surfaces — experiences, avatars, and creator content.
• Develop deep learning models for ranking, retrieval, and personalization using approaches in multimodal models, LLMs, and generative AI.
• Collaborate with applied researchers, engineers, and product teams to advance experimentation and accelerate innovation.
• Translate research into production systems that impact hundreds of millions of daily active users.
• Work backward from user and product needs to deliver ML solutions that drive engagement, retention, and ecosystem growth.

You Have

• Possessing or pursuing a PhD in computer science, engineering, or a related field, with a thesis aligned to Roblox’s research areas.
• Expertise in one or more areas: recommender systems, search systems, information retrieval, or generative models (e.g., LLMs, VLMs, VLAs)
• Ability to design and architect systems for efficient personalization and user interest modeling using advanced attention mechanisms (e.g., sparse/linear attention).
• A strong research track record, evidenced by multiple publications and presentations in top-tier, peer-reviewed venues (e.g., SIGIR, KDD, RecSys, ICLR, ICML, NeurIPS)
• Proficiency in one or more programming languages (e.g., Python, C++, Go, Java) and experience building and optimizing large-scale systems.

Apply now to be considered for anticipated positions.

You may redact age, date of birth, and dates of attendance/graduation from your resume if you prefer.

As you apply, you can find more information about our process by signing up for Speak_. You'll gain access to our practice assessment, comprehensive guides, FAQs, and modules designed to help you ace the hiring process.