Data Scientist II

Microsoft Microsoft · Big Tech · Bengaluru, KA, IN +1 · Data Science

Data Scientist II at Microsoft Security's Identity Threat Detection and Response (ITDR) team, focusing on building AI/ML algorithms for detecting sophisticated cloud-based attacks, anomalies, compromises, and cyber-attacks using Gen AI and graph-based systems. The role involves extensive data analysis, feature engineering with PySpark, and collaboration with researchers and product teams.

What you'd actually do

  1. Build algorithms and innovative methods to discover and defend real world sophisticated cloud-based attacks in SaaS ecosystem.
  2. Collaborate with other data scientists to develop machine learning systems for detecting anomalies, compromises, fraud, and non-human identity cyber-attacks using both Gen AI and graph-based systems.
  3. Identify, integrate multiple data sources, or types of data, and develop expertise with multiple data sources to tell a story, identify new patterns and business opportunities, and communicate visually and verbally with clear and compelling data-driven stories.
  4. Analyze extensive datasets and develop a robust, scalable feature engineering pipeline within a PySpark-based environment.
  5. Work across Threat Researchers, engineering, and product teams to enable metrics for product success.

Skills

Required

  • Python
  • Spark
  • Azure ML
  • SQL
  • KQL
  • Databricks
  • PySpark
  • Classification
  • Prediction
  • Anomaly Detection
  • Optimization
  • Graph ML
  • NLP
  • Cloud computing (Azure/AWS/GCP)
  • Relational Databases
  • Big Data Technologies

Nice to have

  • Generative AI experience

What the JD emphasized

  • 5+ years of programming language experience like C/C++/C/Python required
  • hands on experience in using technologies such as Spark, Azure ML, SQL, KQL, Databricks, etc.
  • Knowledge of Classification, Prediction, Anomaly Detection, Optimization, Graph ML, NLP

Other signals

  • AI/ML for security threat detection
  • Gen AI and graph-based systems
  • Anomaly detection and cyber-attacks