Data Scientist-II

Role Overview: As a Data Scientist-II at Microsoft Security, you will be part of the Defender Experts (DEX) Research team, working on cutting-edge technologies to protect customers from advanced cyberattacks. Your role will involve exploring attacker behavior, operationalizing entity graphs, and developing statistical and ML-driven models to enhance DEX's detection efficacy. Your work will directly contribute to real-time protections used by enterprises and shape the future of Microsoft Security. Key Responsibilities: - Understand complex cybersecurity and business problems, translate them into well-defined data science problems, and build scalable solutions. - Design and build robust, large-scale graph structures to model security entities, behaviors, and relationships. - Develop and deploy scalable, production-grade AI/ML systems and intelligent agents for real-time threat detection, classification, and response. - Collaborate closely with Security Research teams to integrate domain knowledge into data science workflows and enrich model development. - Drive end-to-end ML lifecycle: from data ingestion and feature engineering to model development, evaluation, and deployment. - Work with large-scale graph data: create, query, and process it efficiently to extract insights and power models. - Lead initiatives involving Graph ML, Generative AI, and agent-based systems, driving innovation across threat detection, risk propagation, and incident response. - Collaborate closely with engineering and product teams to integrate solutions into production platforms. - Mentor junior team members and contribute to strategic decisions around model architecture, evaluation, and deployment. Qualifications Required: - Bachelors or Masters degree in Computer Science, Statistics, Applied Mathematics, Data Science, or a related quantitative field. - 6+ years of experience applying data science or machine learning in a real-world setting, preferably in security, fraud, risk, or anomaly detection. - Proficiency in Python and/or R, with hands-on experience in data manipulation (e.g., Pandas, NumPy), modeling (e.g., scikit-learn, XGBoost), and visualization (e.g., matplotlib, seaborn). - Strong foundation in statistics, probability, and applied machine learning techniques. - Experience working with large-scale datasets, telemetry, or graph-structured data. - Ability to clearly communicate technical insights and influence cross-disciplinary teams. - Demonstrated ability to work independently, take ownership of problems, and drive solutions end-to-end.,