Every day, hundreds of millions of customers arrive on Amazon's Homepage, search for a product, and land on a detail page. Along the way, some of what we show them is irrelevant - a recommendation that misreads what they want, a widget that repeats what they just saw, a headline that doesn't say what it means, a product that shouldn't have been surfaced at all. We have built the ability to detect these defects at scale using Large Language Models (LLMs), and we report them to Amazon's most senior leadership as a company-level measure of shopping quality. What we have not yet built is the confidence to act on every one of them.
That is the problem you will own.
Today, the most consequential categories of shopping defects - product quality, duplication, staleness,
irrelevance - go largely unenforced. Not because we cannot detect them, but because we have not
yet clearly defined when they lead to customer dissatisfaction. These are genuinely hard questions. When is a recommendation irrelevant rather than merely unexpected? When are two products duplicates rather than legitimate alternatives? Every answer carries consequences for customers and advertisers.
As Principal Data Scientist, you will own the analytical rigor behind Amazon's store quality metrics end-to-end: how they are defined, how faithfully our LLM implementations execute those definitions, and how accurate the resulting judgments actually are across relevance, presentation, product quality, and duplication. You will go deep enough to inspect individual model judgments and read the edge cases where they break, then come back up to argue definitional questions with the leaders who own the outcomes on both sides. You will also define experiments that will turn judgement into facts backed by data.
Your influence will come from deep dives so well-constructed that stakeholders across two large organizations change their minds. Getting there means building the tooling that makes rigor repeatable rather than heroic: agents that walk the store the way a customer would, automated inspection of experiments, and feedback loops that finally connect what customers tell us directly to the metrics we optimize. Much of the customer voice we already collect goes underused today; you will change that. You will begin on the Homepage, where measurement is most mature, then extend the methodology to Detail Page and Search - carrying not just the metrics but the standard of evidence with them.
Key job responsibilities
- Validate store quality metrics end-to-end: inspect metric definitions, audit LLM implementations, and evaluate LLM judgment accuracy across quality dimensions (relevance, presentation, product quality, duplicates)
- Starting with Homepage, extending cross-page - identify gaps and inconsistencies between Organic and Ads treatments that block the tiered enforcement framework
- Drive alignment through deep dives that present evidence to both Stores and Ads stakeholders
- Build and deliver deep-dive tooling (walk-the-store bots, automated experiment inspection via Gecko, VoC feedback loops) that make metric validation repeatable and self-serve
- Own the analytical rigor behind the alignment on definitions of subjective/debated metrics and moving them to aligned/enforceable
About the team
Core Shopping Data Science owns the measurement of shopping quality across Amazon's Core Shopping eexperiences, including defect metrics reviewed by Amazon's most senior leadership. We focus on the long term and big picture to ensure that the full Amazon shopping experience balances strategic trade-offs. We work across Stores and Advertising, partnering with personalization, ranking, and search teams to turn measurement into changes customers can feel.
BASIC QUALIFICATIONS
You bring a graduate degree in a quantitative field - statistics, computer science, economics, operations
research, or similar - or equivalent depth built through experience, along with substantial industry
experience as a data scientist, including a track record of technical leadership on ambiguous, high-visibility problems. You are fluent in statistical inference, experimental design, and sampling methodology, and you write production-quality code in Python and SQL. You have owned metrics that other organizations made decisions with, and you have defended them under scrutiny.
PREFERRED QUALIFICATIONS
We are especially interested in candidates who have evaluated large language models as judges or annotators and understand where that approach fails; who have driven measurement alignment across organizations with genuinely competing incentives; and who have built the tooling that made their own analysis reproducible for others. Experience with e-commerce search, recommendations, or advertising quality is valuable, as is a history of communicating quantitative findings to senior executives in writing.
The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.
USA, CA, Palo Alto - 217,800.00 - 294,700.00 USD annually
USA, WA, Seattle - 189,400.00 - 256,200.00 USD annually
