Amazon Advertising is one of Amazon's fastest growing and most profitable businesses, responsible for defining and delivering a collection of advertising products that drive discovery and sales. Our products and solutions are strategically important to enable our Retail and Marketplace businesses to drive long-term growth. We deliver billions of ad impressions and millions of clicks and break fresh ground in product and technical innovations every day!
Our team owns personalization, guidance and experimentation science and is placed centrally in the organization which owns the Amazon Advertising Console from UX design to components and services. We leverage a breadth of state-of-the-art techniques such as deep learning, reinforcement learning, LLMs, long term causal modeling as well as sophisticated A/B testing to develop personalized experiences with directly quantifiable business and advertiser success outcomes. We are looking for an accomplished machine learning expert to lead the Applied Science strategy for our recommendation creation and recommendation personalziation program.
In this role, you will work closely with business leaders, stakeholders and cross-functional teams to drive program success through ML-driven solutions. You will shape the data science roadmap, promote a culture of data-driven decision-making, and deliver significant business impact for millions of advertisers worldwide and the company using advanced data techniques and science methodologies.
Key job responsibilities
As an Data Scientist on this team, you will
- Conduct hands-on analysis and modeling of large-scale data to generate insights that boost ads revenue while maintaining a positive advertiser and shopper experience. Present the learning document to stakeholders and leadership to influence their business and technical decisions.
- Lead end-to-end Machine Learning projects that involve high levels of ambiguity, scale, and complexity.
- Explore and prototype multiple approaches to solve the business problem. Conduct proper model evaluation and selection, and propose the best methodology for the use case.
- Run A/B experiments, gather data, and perform statistical analysis to measure the impact of your models.
