Amazon Applied Scientist SB Response Prediction Auction Science Team 

United States, New York, New York 

818285453

Key job responsibilities
As an 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 servingResearch new and innovative machine learning approaches.

- 3+ years of building models for business application experience
- PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
- Experience programming in Java, C++, Python or related language
- Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing

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