Senior Data Scientist Alt Defense

Every day tens of millions of people come to Roblox to explore create play learn and connect with friends in 3D immersive digital experiences all created by our global community of developers and creators.

At Roblox were building the tools and platform that empower our community to bring any experience that they can imagine to life. Our vision is to reimagine the way people come together from anywhere in the world and on any device. Were on a mission to connect a billion people with optimism and civility and looking for amazing talent to help us get there.

A career at Roblox means youll be working to shape the future of human interaction solving unique technical challenges at scale and helping to create safer more civil shared experiences for everyone.

WHY DATA SCIENCE & ANALYTICS

The Data Science & Analytics organizations mission is to increase our speed frequency and acumen of making decisions at scale by instilling a data-influenced approach to building products. We cover a wide area of the data spectrum including analytical data engineering product analytics experimentation causal inference statistical modeling and machine learning. Aligned and partnering with product verticals we use this extensive tool belt to discover new opportunities and unmet use cases influence and shape the product roadmap and prioritization build data products and measure impact on our community of players and developers.

WHY ALT DETECTION

Our Alt Detection system at Roblox is a frontier challenge in large-scale identity modeling managing a massive multi-partite graph that currently includes approximately tens of billions of nodes and hundreds of billions of this role you will apply your expertise in data science statistics and causal inference to strategically define measure and improve our alt detection systems. This is integrated deeply within various applications across the company. Within our Safety group identity modeling is critical to mitigate alternate accounts used by adversarial actors to bypass our safety enforcements. Beyond safety your work will be critical to systemic growth used for core growth reporting and understanding true market penetration in addition to establishing fair creator incentives. And more opportunities to expand this system across safety and non-safety use cases. This is an opportunity to build state-of-the-art detection systems that fuel our safety efforts while directly catalyzing our companys most important growth levers.

You Will:

• Develop ground truth evaluation strategies by integrating diverse signals ranging from gold standard manual labels to automated weak supervision frameworks.
• Calibrate score thresholds across applications balancing high-precision enforcement needs with high-recall required for growth reporting
• Partner with MLE to identify and validate new behavioral network and biometric signals to expand detection coverage.
• Collaborate with Engineering to design modular systems capable of processing billions of candidate pairs and supporting high-concurrency graph traversals.
• Lead the cross-functional integration of identity models into Discovery Ads and Creator Success to eliminate fraud and improve the fidelity of platform metrics.
• Conduct strategic research to decode the incentives behind alt creation and develop sophisticated classification taxonomies to guide mitigation strategies.
• Communicate strategic insights and present recommendations to leadership and all cross-functional partners translating complex statistical findings on prevalence ground truth quality and effectiveness into actionable strategies for Product Engineering Policy Compliance and Legal.
• Partner with ML and Data Engineering teams to ensure model development reporting and detection systems are built on statistically sound ground truth and measurement frameworks.

You Have:

• 8 years of industry experience in data science economics analytics or machine learning engineering
• 6 years of experience using scripting languages (Python R) and big data query/processing languages and tools such as SQL Hive Spark and Airflow
• Knowledge of ML and Deep Learning either via formal training or industry experience
• Ability to apply creative first-principles reasoning to solve ambiguous problems
• Experience developing large-scale safety or moderation systems as well as experience with content platforms specifically user-generated content
• Advanced Degree and/or PhD in Statistics Computer Science Physics Applied Math Economics or other related quantitative fields