Amazon Senior Applied Scientist SB Response Auction 

United States, Washington, Seattle 

401257670

Key job responsibilities
As a Senior Applied Scientist on this team, you typically play a key role in optimizing ad delivery, improving targeting accuracy, and maximizing revenue generation for advertisers, all while maintaining a seamless user experience, you will:- Develop optimization techniques (e.g., multi-objective optimization) to balance multiple goals, such as maximizing revenue for advertisers, increasing user engagement, and maintaining fair ad distribution.
- Build machine learning models, perform proof-of-concept, experiment, optimize, and deploy your models into production; work closely with software engineers to assist in productionizing your ML models.
- Run A/B experiments, fine-tune the models for real-world effectiveness, ensuring that the ad auction system works optimally in production environments.
- Run large-scale experiments to test different auction strategies, bidding algorithms, and ad targeting techniques, using methodologies like multi-arm bandit or reinforcement learning.
- Establish scalable, efficient, automated processes for large-scale data analysis, machine-learning model development, model validation and serving- Research new and innovative machine learning approaches.

- 6+ 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 in building machine learning models for business application
- Understanding of digital advertising ecosystems.
- Familiarity with statistical hypothesis testing, AB testing, and causal inference to ensure robust evaluation of models and experiments.
- Ability to translate business goals (e.g., maximizing ad revenue, improving user experience) into measurable model outputs and performance metrics.

- Knowledge of optimization algorithms for multi-objective problems (e.g., gradient descent, linear programming).
- Strong background in probability theory, game theory, and auction theory (important for designing competitive auction systems).
- Proficiency in reinforcement learning, particularly for decision-making problems like bidding strategies and auction design.