Microsoft Security organization aims to secure digital technology platforms, devices, and clouds in customers' heterogeneous environments and protect them from abuse and fraud.
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 and interest
Responsibilities
- Serve as a domain 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.
- Collaborate cross-functionally with engineering and security teams to operationalize data and feature pipelines for new scenarios.
- Own model lifecycle by monitoring deployed detection models and continuously enhancing detection coverage and reliability.
Other
- Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 2+ years related experience
- Ability to meet Microsoft, customer and/or government security screening requirements
- 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)
- Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field OR equivalent experience
