Microsoft—Principal Applied Scientist - Ads Ranking & Retrieval

Job description

Description: Overview Role: Principal Applied Scientist The AI Economy Team at Microsoft is building the infrastructure that powers how organizations ground, deploy, and scale AI applications. Developers can access it through self-serve, programmatic access, and access at that scale attracts abuse. The AI Economy Trust & Safety team builds the detection behind those access decisions: verifying that customers are who they claim to be, recognizing when many accounts are one actor, and separating ordinary heavy usage from extraction, resale and automated exploitation. You will own the detection problems behind AI Economy access decisions: establishing who is behind a new account when the evidence is thin, recognizing when accounts that look unrelated belong to one actor, drawing the line between heavy legitimate use and systematic extraction, and deciding what should return an approved account to scrutiny after it was cleared. You will work these problems hands-on from end to end, framing the problem, building the models that answer it, and taking them to production. 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. Starting January 26, 2026, Microsoft AI (MAI) employees who live within a 50- mile commute of a designated Microsoft office in the U.S. or 25-mile commute of a non-U.S., country-specific location are expected to work from the office at least four days per week. This expectation is subject to local law and may vary by jurisdiction. Responsibilities - Lead the AI Economy Trust & Safety project end to end, including problem definition, execution planning, technical reviews, production rollout and measurement. - Own the identity-resolution and clustering approach used to connect accounts, tenants and payment instruments to common actors. - Own applicant-risk and ongoing account-risk models, including the evidence used for initial decisions and subsequent reassessment. - Develop detection methods that distinguish legitimate high-volume use from coordinated extraction and other abusive behavior. - Select and evaluate machine learning approaches, including supervised learning, anomaly detection, graph methods, sequence models and large language models. - Establish the evaluation framework for model quality, calibration, false-positive impact, drift, explainability and adversarial robustness, and maintain the associated threat model. - Work with product and engineering counterparts on the AI Economy team to translate detection findings into product controls, and coordinate with privacy, legal and external dependency owners. Qualifications Required/Minimum Qualifications: - Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience (e.g., statistics, predictive analytics, research). - OR Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 4+ years related experience (e.g., statistics, predictive analytics, research). - OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience (e.g., statistics, predictive analytics, research). - OR equivalent experience. Additional or preferred qualifications Other Requirements: Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include but are not limited to the following specialized security screenings: - Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter. Preferred Qualifications: - Experience taking an ambiguous, adversarial problem from first framing through to a deployed system, including the evaluation that proved it worked. - Prior work on know-your-customer, identity proofing, or payment risk in a self-serve or developer-facing product. - A record of mentoring scientists and engineers, and of raising the technical bar across a whole team. - Depth across several modeling families, including graph and network methods, anomaly detection, sequence models and large language models, with evidence for why a given choice held up on adversarial data. - Experience reasoning about attacker economics: what a given control costs the adversary, and where raising that cost changes behavior. - Patents, peer-reviewed publications, or open-source contributions in machine learning, security or risk modeling. - 7+ years experience building fraud, abuse, security or risk detection systems that were delivered into a production environment. This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled. Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.