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 User Behavior

As a Senior Machine Learning Engineer for User Behavior you will build the proactive detection and behavioral intelligence systems that fundamentally shift how Roblox responds to unsafe behavior from reactive punishment to early education-first intervention.

You willown the ML foundation for a new capability at Roblox: identifying users at risk of becoming chronic violators before they escalate and powering the adaptive consequence systems that give them a real chance to change. This is a rare opportunity to build a user-level behavioral intelligence capability that will define how Roblox understands and responds to risk at scale.

You will feel a deep sense of responsibility in building systems that directly affect millions of users especially minors on one of the worlds largest platforms. Your work will reduce harm improve fairness and help ensure Roblox remains a place where creativity and community can thrive safely.

You will:

• Define and Own the ML Vision: Define and lead the multi-year ML vision architectural strategy and execution that identify casual violators early before they escalate and operate reliably under real-world policy and precision constraints.
• Own Behavioral Prediction Models: Develop and maintain production ML models that translate user behavioral signals into actionable risk intelligence enabling earlier and more targeted interventions.
• Build the ML Foundation from Scratch: Design the user feature store training pipelines and model evaluation infrastructure that underpin behavioral ML at Roblox.
• Instrument Experiments for Causal Validity: Partner with XFN stakeholders to ensure A/B tests on intervention variants have proper random assignment and instrumentation for future causal model training. This data cannot be retroactively collected.
• Drive End-to-End Product Development: You will not just model; you will build. You will work cross-functionally to construct datasets from scratch where none exist build labeling pipelines and ship solutions to various product surfaces.
• Ship Code Not Just Models: Expect to own end-to-end delivery building and operating ML pipelines from training and offline evaluation through production serving. You will integrate your models directly into the stack alongside SWE.

You have:

• 5 years of experience building and shipping production ML systems at scale.
• Hands-on experience with ML classification at scale including traditional ML models sequence modeling on user-event data and/or LLM-based approaches with strong intuition for model evaluation on real-world data.
• Proficiency designing and maintaining feature pipelines and feature stores for behavioral or event-driven data.
• Experience building embedding-based retrieval systems (ANN / vector search) in production.
• Experience building and operating end-to-end ML pipelines: training offline evaluation A/B experiment hooks and production serving infrastructure.
• Strong understanding of ML experiment design including training data validity label quality recall/precision tradeoffs under constrained thresholds and causal inference fundamentals.
• Nice to have: experience in Trust & Safety user behavior modeling or user understanding (e.g. churn prediction engagement modeling risk scoring); familiarity with uplift/causal ML; sequence models on user-event data.

You are:

• A Visionary Architect: Capable of synthesizing complex business and safety goals into a clear compelling and actionable technical strategy.
• A Pragmatic Builder: You are scrappy and impact-oriented. You view undefined data and messy systems as opportunities to build structure rather than blockers to progress.
• Comfortable with Ambiguity: You thrive in undefined or open-ended problem spaces providing structure clarity and decisive direction to your teams.
• An Inspiring Leader: Passionate about developing the next generation of technical leaders managers and engineers.
• An Executive Communicator: Highly effective at communicating complex technical concepts to both engineering teams and non-technical executive leadership.
• Committed to Ethical AI: Dedicated to building ML systems that are fair transparent and operate with the utmost responsibility toward user safety and platform civility.