About this role
Description
The Cross-Border (XB) Science & Analytics team is at the heart of Amazon's international marketplace expansion, powering science-driven solutions that enable customers across 20+ countries to discover and purchase products seamlessly across borders. Our work directly impacts millions in annualized business value through ML models, algorithms, and data-driven systems that solve some of Amazon's most complex cross-border challenges.
We are a lean, high-impact team of scientists working across various programs spanning search ranking, demand forecasting, pricing optimization, product recommendations, language understanding, and generative AI. We partner closely with product, engineering, and business teams across Amazon's global retail organization to take science from ideation to production at scale.
Key job responsibilities
We are looking for a passionate and technically strong Applied Scientist to join our team. In this role, you will design, develop, and deploy machine learning models and algorithms that directly improve the cross-border shopping experience for millions of Amazon customers worldwide. You will work on challenging, ambiguous problems—from improving search relevance across languages to building ML-powered pricing and recommendation systems—with significant autonomy and end-to-end ownership.
This is a hands-on, high-visibility role. You will publish your research internally and externally, collaborate with world-class scientists and engineers, and see your work go live across Amazon's global marketplaces.
A day in the life
Research & Experimentation
Analyze large-scale datasets to identify patterns, formulate hypotheses, and design experiments
Develop and iterate on ML models (deep learning, NLP, ranking, causal inference) to improve cross-border product discovery, relevance, and conversion
Design and run A/B experiments on live traffic to measure model impact against business and customer metrics
Building & Shipping
Write production-quality code (Python, Java/Scala) and work with SDEs to deploy models into real-time and batch inference pipelines
Build end-to-end ML pipelines—from data ingestion and feature engineering to training, evaluation, and online serving
Own model monitoring, performance debugging, and iterative improvements post-launch
Collaboration & Communication
Participate in weekly science syncs, design reviews, and cross-functional standups with product managers, engineers, and business stakeholders
Translate business problems into well-defined science problems, and communicate results and trade-offs to both technical and non-technical audiences
Contribute to technical documentation—architecture wikis, experiment write-ups, and model cards
Growth & Community
Present at internal ML paper reading sessions and science forums
Stay current with state-of-the-art research (NeurIPS, ICLR, ACL, KDD) and bring new ideas to the team
Mentor junior scientists and interns; participate in hiring interviews and debriefs
Publish findings in top-tier venues and file patents where applicable
Basic Qualifications
- 3+ years of building models for business application experience
- PhD, or Master's degree
- Experience in patents or publications at top-tier peer-reviewed conferences or journals
- 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 using Unix/Linux
- Experience in professional software development
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.