SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 328,610 - 399,420 / annual
Roblox is seeking a Principal Machine Learning Engineer to lead the Alt Defense pod within the Safety organization. This role focuses on building an industry-leading alternate account detection system that operates at massive scale—processing billions of accounts and identifying recidivism within minutes.
You will architect and lead the technical vision for the alternate account detection platform, moving from reactive measures to proactive, near real-time prevention. Key responsibilities include:
• Architect high-scale ML systems using Graph Neural Networks (GNNs) and advanced clustering techniques to map relationships across billions of entities
• Solve complex ground truth and training data challenges for adversarial use cases
• Build for latency and scale, ensuring detection happens within minutes of a bad actor's attempt to rejoin the platform
• Develop innovative adversarial approaches to stay ahead of sophisticated actors using evolving identity-masking techniques
• Drive the ML roadmap, identifying opportunities to leverage big data and behavioral signals to improve precision and recall in a high-stakes environment
• Mentor and up-level a pod of high-performing ML and software engineers, fostering technical excellence and rapid iteration
You will report to the Senior Engineering Manager of the Account Identity Team. The role is hybrid, with office presence required Tuesday, Wednesday, and Thursday at Roblox's San Mateo headquarters.
REQUIREMENTS:
• MS or PhD degree in Computer Science, Machine Learning, or related field
• 10+ years of industry experience in Applied ML, with significant focus on anti-abuse, fraud, integrity, or identity
• Deep expertise in Graph Learning: Large-scale GNNs (GraphSAGE, PGB, etc.) and unsupervised/semi-supervised clustering at billion-node scale
• Proven track record leading complex technical projects from conception to production-level deployment
• Experience with high-throughput systems and deploying ML models in low-latency environments where time-to-detect is critical
• Adversarial mindset: ability to think like a bad actor to anticipate circumvention techniques and build robust defenses
• Resourcefulness, analytical rigor, user-oriented thinking, team orientation, and mission focus on safety at scale
