Senior Data Scientist

Microsoft•Redmond, WA

27d

About The Position

Overview Organization & Team Microsoft’s Identity organization secures hundreds of millions of daily signins and protects missioncritical services at global scale. We’re hiring a Senior Data Scientist to advance adaptive threat detection at the edge and resilience of origin services—designing models that detect and mitigate abusive patterns in real time, improving customer safety and service reliability. Role Overview Every day, hundreds of millions of people rely on Microsoft services such as Microsoft 365, Azure, Xbox, and Outlook.com. Behind the scenes, Microsoft’s Edge team works continuously to protect those users from account compromise, fraud, and abuse. Our data science team sits at the core of this mission, building and operating machine-learning–driven protections that stop malicious actors at global scale. In this role, you will lead end-to-end data science efforts, from signal design and feature engineering through model training, online scoring, and experiment evaluation. You will work across two strategic problem areas: Behavior-driven intelligent blocking: Learn patterns from authentication and access signals to automatically reject malicious activity such as password spraying or account enumeration, while minimizing false positives. Volume-driven origin protection: Identify and throttle anomalous traffic surges to protect upstream services from degradation and ensure fair usage. You will dive into terabytes of data to understand an ever-evolving threat landscape, turning a blank canvas of signals into robust, production-ready detections that balance strong security with a seamless user experience. You’ll partner closely with applied scientists, software engineers, and product leaders across Identity and edge services to ship measurable, real-world protection improvements. If you’re passionate about big data, machine learning, and fraud detection—and motivated by the opportunity to protect millions of users as part of a mission-driven, highly collaborative team—this role offers both scale and impact. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Requirements

Doctorate in Data Science, Mathematics, Statistics, Econometrics, Economics, Operations Research, Computer Science, or related field AND 1+ year(s) data-science experience (e.g., managing structured and unstructured data, applying statistical techniques and reporting results) OR Master's Degree in Data Science, Mathematics, Statistics, Econometrics, Economics, Operations Research, Computer Science, or related field AND 3+ years data-science experience (e.g., managing structured and unstructured data, applying statistical techniques and reporting results) OR Bachelor's Degree in Data Science, Mathematics, Statistics, Econometrics, Economics, Operations Research, Computer Science, or related field AND 5+ years data-science experience (e.g., managing structured and unstructured data, applying statistical techniques and reporting results) OR equivalent experience.
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 Cloud background check upon hire/transfer and every two years thereafter.

Nice To Haves

MS/PhD in computer science, machine learning, statistics, or quantitative domain
Expertise in Python (or Scala/R) and ML tooling (e.g., PyTorch, scikitlearn, Spark); strong SQL skills for largescale analysis. Hands on experience with anomaly detection, timeseries, class imbalance techniques, and online evaluation in realtime systems.
Demonstrated strength in experiment design (A/B, CUPED or equivalent), causal inference basics, and metric stewardship.
Proven ability to collaborate across engineering, product, and operations; clear written and verbal communication with executive and technical audiences.
Background in security, antiabuse, fraud prevention, threat intelligence or traffic defenses at internet scale.
Experience with streaming and telemetry platforms (e.g., Kafka/Event Hubs), feature stores, and MLOps (training, deployment, monitoring).
Familiarity with edge/proxy concepts (rate limiting, backpressure, routing), and reliability practices (SLOs, error budgets).

Responsibilities

Design, build, and operate machine-learning–based detections to prevent fraud and abuse across Microsoft Identity services.
Lead signal and model design by defining features, labels, heuristics, and training approaches using supervised and unsupervised techniques.
Analyze large-scale authentication, access, and traffic data to identify emerging abuse patterns and translate them into automated detections.
Productionize models for low-latency online scoring, implementing guardrails, dynamic thresholds, and safety mechanisms to minimize customer impact.
Design and analyze experiments (A/B tests, holdouts) to evaluate detection effectiveness and quantify tradeoffs such as false positives and false negatives.
Define and monitor key metrics and dashboards to track model performance, data quality, and drift, enabling rapid iteration and response.
Partner cross-functionally with engineering, product, and security teams to harden pipelines, align on success metrics, and support incident response and investigations.
Document designs and findings clearly and contribute to reviews, readiness checks, and continuous improvement of detection systems.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume