Applied Scientist, Advertising, AMPI Measurement

Description

Amazon is investing heavily in building a world-class advertising business, and we are responsible for defining and delivering a collection of advertising tools and products that drive discovery and Advertiser success. Our products are strategically important to our Retail and Marketplace businesses, driving long-term growth. We deliver billions of ad impressions and millions of clicks daily and are breaking fresh ground to create world-class products.

We are highly motivated, collaborative, and fun-loving with an entrepreneurial spirit and bias for action.

The Marketing Effectiveness & Measurement Science team develops causal inference and machine learning systems to measure the impact of marketing programs across Amazon's advertising ecosystem. We build production-grade measurement models and the calibration system that serves as the measurement truth layer - continuously validating model outputs against RCTs and certifying them for high-stakes business and finance decisions. As our signals increasingly feed automated, machine-speed consumers, we are also transforming how we operate: building AI-assisted pipelines and agents that automate onboarding, backfills, diagnostics, and reporting so scientists can focus on judgment and method.

Our work sits at the intersection of econometrics, scalable and reliable ML systems, calibration, and high-stakes business decisions.

As an Applied Scientist on this team, you will own end-to-end modeling and production pipelines - from problem formulation and experimental design through model development, productionization, calibration, and stakeholder communication - increasingly augmented by AI tooling and agents.

Major responsibilities include:

Translate / Interpret

Partner with cross-functional teams to translate business questions into rigorous causal inference problems

Design observational studies and quasi-experiments to measure marketing effectiveness when traditional A/B tests are infeasible

Work with data engineering to instrument new data pipelines when existing data cannot answer the causal question

Measure / Quantify / Expand

Own and evolve production attribution models across multiple marketing channels, with the reliability, latency, and reproducibility that automated downstream consumers depend on

Build and maintain causal inference pipelines using methods such as Difference-in-Differences, Synthetic Control, Double Machine Learning, and Media Mix Models

Develop and maintain calibration systems that benchmark model outputs against RCTs - owning the measurement truth layer

Write scalable, modular, SDE-standard PySpark/Python codebases (CI/CD, test isolation, structured logging) that process large-scale event data and deploy to production with confidence

Continuously improve model accuracy through feature engineering, heterogeneity analysis, and sensitivity testing

Explore / Enlighten

Investigate anomalies in model outputs and deep-dive to identify root causes

Research and prototype next-generation measurement methods and apply AI/LLM-based tooling to accelerate the science development lifecycle

Make Decisions / Recommendations

Present findings to senior leadership with clear recommendations

Build dashboards, agent-consumable APIs, and self-service tools that let stakeholders (and downstream systems) explore results independently

Write production-quality Python for data analysis, model training, calibration, and result publishing

Basic Qualifications

- 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

Preferred Qualifications

- Experience in professional software development

- Experience in designing experiments and statistical analysis of results

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Our inclusive…