Principal Applied Scientist

Full Job Description

Identify emerging fraud tactics, adversary infrastructure, and evasion patterns across monetization flows and LLM-native systems through threat modeling, behavioral, graph-based, temporal, and cross-surface big data analysis. Assess high-risk assumptions and attack paths by forming explicit threat hypotheses, identifying observable signals, and validating risk through structured modeling, targeted experiments, and quantitative measurement. Design safe adversarial simulations that expose blind spots, then convert the results into test harnesses, monitored indicators, and reproducible regression scenarios for sister defense teams. Establish authoritative ground truth by correlating evidence across accounts, traffic, transactions, providers, devices, and infrastructure; reconstruct attack chains and document their provenance, confidence, scale, and economic exposure. Develop shared investigation infrastructure, agent-assisted services, and reusable libraries for telemetry analysis, entity resolution, attack-sequence reconstruction, and reproducible case analysis and convert into actionable insights. When material incidents occur, lead end-to-end reconstruction, document actionable findings, and support the sister teams responsible for remediation and enforcement through validation of closure. Shape the scientific and technical strategy for monetization fraud intelligence, validation, and investigation capabilities across organizational boundaries. Embody our Culture and Values. 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) These requirements include but are not limited to the following specialized security screenings: Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 9+ years related experience (e.g., statistics, predictive analytics, research) OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience (e.g., statistics, predictive analytics, research) OR equivalent experience. Demonstrated experience proactively identifying and investigating adversarial abuse at web scale through hypothesis-driven analysis of large-scale traffic or transaction telemetry and entity resolution across complex ecosystems. Demonstrated ability to produce written technical assessments that stand up to scrutiny, stating mechanism, evidence, confidence and economic impact clearly enough for engineering and executive audiences to act on. Demonstrated experience developing and evaluating machine learning or statistical detection methods on large-scale telemetry, including label validation and measurement of precision, recall, coverage, and drift; and shipping production services or data pipelines using Python and large-data tools such as Spark or SQL. Direct experience with advertising or monetization fraud ecosystems, including invalid traffic detection, OpenRTB and supply-path mechanics, click and conversion fraud, botnets, device spoofing, residential proxy networks, or synthetic identity abuse. Red team, offensive security, or adversarial simulation experience, with a track record of designing safe attack simulations and converting findings into reusable regression tests rather than one-off exploits. Working knowledge of LLM-native attack surfaces and agent-assisted analysis tooling, with experience in relevant methods such as structured threat modeling, graph analysis, anomaly detection, controlled experimentation, attack replay, FMEA, or STPA. Experience influencing outcomes across organizational boundaries, where the evidence you produce is acted on by teams that own remediation and enforcement rather than by your own team.