Machine Learning Scientist / Applied Scientist, EU Prime and Marketing Analytics & Science (PRIMAS)

Are you interested in changing how Amazon does marketing — moving beyond platform-optimized broad reach to campaigns that find the right customer, at the right moment, using Amazon's unmatched 1P data?

We are seeking an Applied Scientist to join PRIMAS (Prime & Marketing Analytics and Science). In this role, you will design and run the experiments that answer the foundational question for EU marketing: does adding 1P audience signal on top of Value-Based Optimization (VBO) improve marketing efficiency — and if so, for which customer cohorts, on which surfaces, and at what scale?

Amazon's current marketing model is largely platform-led: we set objectives and let platforms optimize toward conversion. This approach works well for broad acquisition but systematically underserves lifecycle goals — it cannot distinguish between a Bargain Hunter who will never pay full price and a high-potential customer one nudge away from becoming a Prime member. This role sits at the center of changing that. You will build the 1P audiences, design the experiments that test them, and generate the evidence that guides how Amazon allocates hundreds of millions in marketing spend.

Year 1 is an experimentation year. You will deploy 1P audiences across multiple surfaces and channels — Meta, Google, Amazon Display Ads — and measure incrementally against VBO baselines. The goal is not to replace platform optimization but to understand when and where the combination of 1P signal + VBO outperforms VBO alone, and to build the experimental infrastructure that makes this learning scalable.


Key job responsibilities
1P Audience Development & Experimentation:

- Build and validate 1P audience segments from Amazon behavioral, transactional, and lifecycle data
- Design experiments that isolate the incremental effect of 1P audience signal over platform VBO baselines
- Deploy audiences across activation surfaces and establish measurement standards that make cross-surface comparison valid

Causal Measurement & Incrementality:
- Apply causal inference methods to measure the true incremental lift of audience-based targeting vs. VBO
- Develop power analysis frameworks and guardrails that enable rapid experimentation without underpowered or conflated tests
- Deliver optimization recommendations grounded in experimental evidence: which cohorts respond, which surfaces deliver, which creative strategies drive behavior change

Scaling the Learning:

- Build reusable audience and measurement frameworks that can be deployed across campaigns and channels — year 1 experiments should produce infrastructure, not one-off analyses
- Document experimental learnings in a way that informs both the 2026 roadmap and the business case for investing further in 1P audience capabilities in 2027+
- Partner with engineering and PMT to translate validated audience prototypes into production-ready solutions that scale beyond the experimentation phase



About the team
The PRIMAS team, is part of a larger tech tech team of 100+ people called WIMSI (WW Integrated Marketing Systems and Intelligence). WIMSI core mission is to accelerate marketing technology capabilities that enable de-averaged customer experiences across the marketing funnel: awareness, consideration, and conversion.

Basic Qualifications

- Experience in patents or publications at top-tier peer-reviewed conferences or journals
- Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing
- Experience building machine learning models or developing algorithms for business application
- Experience with programming languages such as Python, Java, C++
- PhD in computer science, machine learning, robotics, statistics, mathematics, operations research, engineering, or equivalent quantitative field

Preferred Qualifications

- Experience in professional software development
- Experience in designing experiments and statistical analysis of results
- Experience in solving business problems through machine learning, data mining and statistical algorithms

Amazon is an equal opportunities employer. We believe passionately that employing a diverse workforce is central to our success. We make recruiting decisions based on your experience and skills. We value your passion to discover, invent, simplify and build. Protecting your privacy and the security of your data is a longstanding top priority for Amazon. Please consult our Privacy Notice (https://www.amazon.jobs/en/privacy_page) to know more about how we collect, use and transfer the personal data of our candidates.

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.