As a Senior Machine Learning Engineer on the Engine Security Behavioral Detection team, you will focus on building scalable ML systems to detect malicious behavior, automated play, and exploits using real-time or offline analysis to ensure platform safety and integrity. You will be at the forefront of protecting the Roblox community, developing sophisticated models that distinguish between legitimate player interactions and adversarial activities in a massive, dynamic 3D ecosystem. You will own the lifecycle of detection models, from identifying emerging threat patterns to deploying high-throughput inference services. Your work will bridge the gap between complex behavioral analysis and system-wide mitigation, ensuring that Roblox remains a safe and fair environment for millions of creators and players globally.
You Will:
- Design and implement end-to-end ML pipelines for anomaly detection and behavior analysis.
- Develop and deploy models that can identify complex, adversarial bot patterns and game exploits.
- Work on real-time or offline inference systems that can mitigate malicious activity without disrupting user experience.
- Collaborate with security teams, data scientists, and backend engineers to harden the platform against evolving threats.
You Have:
- PhD or Master's in Computer Science, Data Science, or related field.
- 4+ years of experience in ML engineering, specifically in behavior modeling, anomaly detection, or fraud detection.
- Proficiency with time-series analysis, neural networks, or large-scale classification systems.
- Experience training and deploying models on high-throughput, low-latency production systems.
- Proficiency in Python (PyTorch/TensorFlow) and familiarity with big data processing frameworks (e.g., Spark, Flink, or similar).
- Strong problem-solving skills and a passion for platform integrity and security.
Job Expectations:
- Deliver high-impact ML solutions that directly improve platform security and trust.
- Take ownership of model monitoring and retuning strategies to counter adaptive adversary tactics.
- Provide technical guidance on best practices for feature engineering in adversarial domains.
- Maintain operational excellence, ensuring reliability and scalability of detection services.
For roles that are based at our headquarters in San Mateo, CA: The starting base pay for this position is as shown below. The actual base pay is dependent upon a variety of job-related factors such as professional background, training, work experience, location, business needs and market demand. Therefore, in some circumstances, the actual salary could fall outside of this expected range. This pay range is subject to change and may be modified in the future. All full-time employees are also eligible for equity compensation and for benefits as described on
this page.
Annual Salary Range
$295,250-$345,040 USD
Roles that are based in an office are onsite Tuesday, Wednesday, and Thursday, with optional presence on Monday and Friday (unless otherwise noted).
