Microsoft Security aspires to make the world a safer place by reshaping security and empowering users, customers, and developers with a security cloud. The Central Fraud and Abuse Risk (CFAR) team builds innovative, intelligent, and scalable risk solutions to protect Microsoft's customers and services from abuse and fraud, relying on state-of-the-art machine learning and large-scale information aggregation to detect evolving fraud patterns.
Requirements
- 2+ years of Data Science or Machine Learning experience in handling high volumes of structured and unstructured data
- 2+ years of extensive programming experience in at least one of the following languages: C-Sharp, Python, or similar language
- 2+ years of data querying experience in SQL, Kusto (KQL) or similar languages
- Familiarity with ML tools & frameworks such as PySpark, Scikit-Learn, PyTorch etc.
- Familiarity with experiment design and applied machine learning for predicting outcomes in large-scale, complex datasets.
- Experience in cloud services with prior exposure to Big Data technologies is desirable but not required.
- Security and Fraud domain experience.
Responsibilities
- Build machine learning pipelines
- Vet experiments
- Incorporate quality monitors
- Ship successful models to production
- Contribute as a subject matter expert in machine learning, statistics, and experiment design.
- Drive fraud detection by researching evolving behaviors, identifying features with threat analysts, and applying scalable detection strategies.
- Own model lifecycle by monitoring deployed detection models and continuously enhancing detection coverage and reliability.
Other
- 3 days / week in-office
- Travel 0-25%
- Ability to meet Microsoft, customer and/or government security screening requirements are required for this role.
- Microsoft Cloud Background Check: This position will be required to pass the Microsoft background and Microsoft Cloud background check upon hire/transfer and every two years thereafter.
- 1+ year(s) experience creating publications (e.g., patents, peer-reviewed academic papers).
