Description

The Ads Measurement Science team within Amazon Ads' Measurement, AdTech, and Data Science (MADS) organization
serves a centralized role developing solutions for a multitude of performance measurement products to measure the full impact of advertiser spend, including both online and offline sales impacts across all timeframes. It delivers actionable insights for advertisers to optimize media portfolios. We also build science solutions for AI and AI-powered tools that unlock new insights and automate high-effort customer workflows for ad measurement, such as custom query and report generation based on natural language user requests. We leverage new technologies including Generative AI, machine learning, causal inference, natural Language Processing (NLP), and Computer Vision (CV) to drive these innovations.

A key focus of this role is Modeled Attribution, Amazon's privacy-compliant measurement system serving millions of advertisers and processing billions of events monthly across global marketplaces. We apply state-of-the-art machine learning and GenAI techniques to generate accurate measurement when user identity is unavailable, representing Amazon's technical response to industry-transforming privacy regulations and platform changes.

As an Applied Scientist II on the team, you will develop modeled measurement solutions end-to-end from inception to production. You will propose, design, analyze, and productionize models to provide novel measurement insights to our customers. Your work will directly enable advertisers to continue optimizing their campaigns effectively as the digital ecosystem undergoes significant privacy-driven changes, and provide event-level attribution signals that empower ad optimization teams to enhance campaign performance and monetization on traffic without identity.


Key job responsibilities
* Leverage deep expertise in one or more scientific disciplines to invent solutions to ambiguous ads measurement problems
* Disambiguate problems to propose clear evaluation frameworks and success criteria
* Develop modeled attribution solutions using deep learning, transformers, and large language models to fill measurement gaps in privacy-constrained environments
* Work autonomously, write high-quality technical documentation and present findings to both technical and business stakeholders
* Implement a significant portion of critical-path code, and partner with engineers to directly carry solutions into production
* Partner closely with other scientists to deliver large, multi-faceted technical projects
* Share and publish works with the broader scientific community through meetings and conferences
* Communicate clearly to both technical and non-technical audiences
* Partner with engineers to optimize model performance, reduce latency, and ensure operational excellence for systems serving millions of customers
* Contribute to the team's scientific direction by proposing novel approaches to measurement challenges
* Mentor junior scientists and participate in the hiring process to raise the team's technical bar

About the team
We are a team of scientists across Applied, Research, Data Science and Economist disciplines. You will work with colleagues with deep expertise in ML, NLP, CV, Gen AI, and Causal Inference with a diverse range of backgrounds. Our work combines rigorous scientific experimentation with practical engineering. We publish at top-tier conferences while building production systems that process trillions of events annually. We partner closely with top-notch engineers, product managers, sales leaders, and other scientists with expertise in the ads industry and on building scalable modeling and software solutions.