Design and deploy advanced machine learning systems for device identification, anomaly detection, and fraud prevention—balancing precision, recall, and real-world adversarial dynamics.
Contribute to the development of scalable data pipelines and production ML workflows using structured and unstructured telemetry (e.g., browser, mobile, session data).
Investigate high-complexity signals (e.g., emulator use, spoofing, low-entropy fingerprints), applying advanced statistical methods and domain knowledge to detect fraud and abuse.
Translate ambiguous business problems into modeling approaches, using a combination of supervised, unsupervised, and heuristic techniques.
Partner with engineering, product, and risk teams to contribute to data architecture decisions, signal collection, and planning.
Drive experimental design, A/B testing frameworks, and robust validation techniques to ensure model generalizability and long-term trust.
Contribute to team standards for ML explainability, risk evaluation, and feature logging.
Document methodologies and communicate results effectively through dashboards, presentations, and reports for both technical and executive audiences.
Mentor junior data scientists and participate in cross-functional working groups.
Requirements
Master’s degree (or equivalent practical experience) in Computer Science, Machine Learning, Statistics, or a related quantitative field.
6+ years of experience in data science or applied machine learning, including experience working in production environments.
Excellent SQL skills and extensive experience with large-scale databases and data modeling.
Proven track record of deploying and maintaining ML models in live systems, ideally involving streaming or near-real-time data.
Proficiency in Python and distributed computing tools (e.g., Spark, PySpark).
Hands-on experience with ML frameworks such as scikit-learn, XGBoost, TensorFlow, or similar.
Excellent communication skills—able to explain complex technical results to non-technical stakeholders and senior leadership.
Experience designing and interpreting experiments, working with real-world noisy datasets, and applying sound validation techniques to assess model robustness.
Demonstrated ability to break down ambiguous problems, apply analytical rigor, and uncover meaningful insights that influence product or risk strategies.
Strong judgment across data quality, model selection, and business impact tradeoffs.
Collaborative mindset and experience working cross-functionally with product, engineering, and analytics teams.