Product Manager, Sift

• 3-5 years of Product Management experience in the ML and fraud prevention space
• Strong and proven experience with ML and ML model releasing and serving, including ensuring data quality, and performance monitoring
• Track record in translating business and user experience metrics onto ML metrics
• Program management capabilities
• Proven ability to manage ML model lifecycle and feature extraction
• Experience collaborating closely with engineers, data scientists, and customers
• Comfortable working with Marketing and Sales teams to launch new product features and drive their adoption

Desirable

• We are looking for a Product Manager to lead our ML and ML Operationalization efforts
• This role focuses on driving fraud risk score accuracy and stability, including our flagship capability, RiskWatch
• Advocate for customer and business impact, while influencing and guiding the highly technical ML teams to deliver an easily explained measurable customer value
• You will be responsible for ML model release and serving, as well as feature extraction. On the ML operationalization side, you will support model releases and work with customers on customer-specific calibration and ML integration
• Own Sift’s Machine Learning Vision: collaborate with Engineering Leaders to increase customer value and simplification of our ML
• Oversee our Machine Learning outcomes: measure and monitor customer KPIs and advise ML research, development, and operations to improve said KPIs
• Drive Fraud Risk Score Accuracy & Stability: Ensure the accuracy and stability of fraud risk scores, including managing RiskWatch
• ML Model Release and Servicing: Oversee the release and servicing of ML models, ensuring they meet performance and reliability standards
• Feature Engineering, Model Development, and Third-Party Data Integration: lead all aspects of enhancing model performance and help advocate and prioritize work that maximize customer impact
• Customer-Specific Calibration and ML Integration: Work closely with customers to calibrate models to their specific needs and integrate ML solutions into their systems

• Introduction interview with the recruiter (30 minutes)
• Product strategy discussion with Senior Director of Product Management (45 minutes)
• Technical interviews with Engineering Leaders (45 minutes)
• Winning customer experience discussion with Chief Product Officer (30 minutes)
• Values and behavior-based interview with Senior Director, People Partner (45 minutes)