Senior Applied Scientist - Predictive Scoring, AWS Marketing Science

About the role

The AWS Marketing Science team builds the ML models and measurement systems that drive marketing decisions across Amazon Web Services. We own incrementality and valuation, ROI measurement, marketing attribution, propensity scoring, account and lead clustering, and next-best-action models. Our work directly influences how AWS allocates marketing spend, targets accounts, and measures effectiveness across billions in pipeline.

Responsibilities

• Design and deploy predictive lead scoring models to optimize customer acquisition, conversion, and retention strategies using advanced techniques like survival analysis, graph networks, or transformer-based architectures.
• Architect end-to-end ML pipelines for large-scale deep learning models, including data preprocessing, distributed training, model optimization, and real-time inference.
• Publish research, file patents, and stay ahead of industry trends in the marketing science, propensity modeling, and customer journey prediction domains.
• Innovate in multi-modal modeling (text, graph, behavioral, and temporal data) to enhance scoring accuracy across account and lead levels.
• Conduct rigorous A/B testing, causal inference, and counterfactual analysis to measure model impact and iterate rapidly.
• Collaborate with MLOps engineers to streamline model deployment, monitoring, and retraining using tools like AWS SageMaker, or MLflow and other internal tools.
• Participate in science reviews to raise the science bar in our organization. This includes reviewing your work and the work of others.
• Mentor junior scientists on ML methodology, experimentation design, and production best practices.
• Define offline and online evaluation frameworks; establish success metrics tied to business outcomes (conversion rates, pipeline generation).

Qualifications

• 3+ years of building machine learning models for business application experience
• PhD, or Master's degree and 6+ years of applied research experience
• Experience programming in Java, C++, Python or related language
• Experience with neural deep learning methods and machine learning
• Knowledge of deep learning, machine learning and statistics
• Experience engaging, verbally and in writing, with internal and external stakeholders to convey complex ideas in a clear, concise manner
• Proficiency in Python and ML frameworks (PyTorch, TensorFlow, or equivalent)
• Real world experience in recommender systems, transformers, or multi-objective tasks
• Strong background in statistical analysis, experimental design, and SQL/Spark for big data processing
• Extensive knowledge in a breadth of machine learning topics