Crunchyroll is looking to detect account sharing fraud to enhance subscriber growth and revenue optimization.
Requirements
- Expert in Python and frameworks like TensorFlow, PyTorch, or XGBoost
- Proficiency in MLOps tools such as MLflow, Docker
- Experience with cloud services like AWS SageMaker, Databricks MLFlow
- Experience with cloud computing infra and tooling such as AWS/GCP
Responsibilities
- Design and implement machine learning algorithms, including anomaly detection models, to identify unauthorized account sharing in real-time.
- Develop end-to-end ML pipelines for data preprocessing, model training, evaluation, and deployment using cloud platforms.
- Optimize models for performance, scalability, and efficiency to handle high-volume streaming data.
- Integrate ML solutions with existing systems via APIs and establish monitoring for model drift and retraining.
- Collaborate on A/B testing and iteration to refine algorithms based on feedback and evolving evasion tactics.
Other
- 5+ years of hands-on experience in ML engineering, with a track record in fraud or anomaly detection systems, ideally in online, consumer facing products and services.
- Experienced in working with data scientists, engineers, and product teams to deploy models that support business goals like revenue optimization.
- Strong ability to document technical processes and explain algorithm decisions to diverse stakeholders for seamless integration.
- Excellent verbal and written communication skills, with the ability to convey complex technical concepts to non-technical stakeholders.
- Possess a master's degree in computer science, machine learning, or a related quantitative field, with certifications in cloud ML being a plus.
