About this role
Description
We are embarking on a multi-year journey to improve the shopping experience for customers globally. Amazon Search team creates customer-focused search solutions and technologies that make shopping delightful and effortless for our customers. Whenever a customer visits an Amazon site worldwide and types in a query or browses through product categories, Amazon Search services go to work. We design, develop, and deploy high performance, fault-tolerant distributed search systems used by millions of Amazon customers every day. Our Vertical Search Relevance team works to enable a great search experience for customers regardless of the product category they are shopping.
We are seeking a strong Senior Applied Scientist to join the Vertical Search Relevance team. This team's charter is to develop micro-experiences that serve customers' vertical-specific (category) needs, identify opportunities in high-growth and strategic verticals, and build the signals, algorithms, and machine-learning framework used to train and evaluate the relevance models that power search across all of Amazon's verticals. In this role, you will set the science direction for vertical search relevance, leading the invention of ranking features and modeling techniques, improving the machine-learning framework used for training and offline evaluation of new relevance models, and raising the bar on how the team takes on and delivers large, ambitious projects. Your solutions should work across all languages and locales that Amazon supports and will be used worldwide.
Key job responsibilities
As a Senior Applied Scientist on the team, you will lead science innovation to improve the customer search experience across verticals. You will:
- Build and deploy machine learning models for Product Search ranking and relevance that serve billions of search requests.
- Develop new ranking features and techniques, building on the latest results from the academic research community.
- Design and train semantic matching and ranking models (bi-encoders, cross-encoders, and distillation from large foundation models) for relevance and vertical search result experiences.
- Train multi-objective ranking and scoring systems that balance relevance, diversity, and specificity for category-specific needs.
- Design and implement scalable model architectures optimized for strict latency constraints including knowledge distillation, quantization, and efficient inference strategies for production deployment.
- Propose and validate hypotheses to direct the business and product roadmap.
- Own the full development cycle: design, development, impact assessment, A/B testing (including interpretation of results), and production deployment.
- Lead end-to-end science projects from problem formulation through production launch, mentoring scientists and collaborating closely with engineers and partner teams within and outside Amazon Search to deliver customer-facing impact.
- Be a leader. Use your expertise to set a high bar for the team, mentor team members, and set the tone for how to take on and deliver large projects.
- Be customer focused. Work backwards from customer problems, figure out elegant solutions, and implement them for speed and scalability.
Basic Qualifications
- PhD, or Master's degree and 6+ years of applied research experience
- Experience programming in Java, C++, Python or related language
- 6+ years of building machine learning models or developing algorithms for business application experience
- Experience with neural deep learning methods and machine learning
Preferred Qualifications
- Experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy etc.
- Experience with large scale distributed systems such as Hadoop, Spark etc.