About the job
The AWS Marketplace team is looking for an Applied Scientist to help build and improve our AI/ML-Powered Discovery systems. The ideal candidate is passionate about applying machine learning and artificial intelligence to complex information retrieval challenges, with experience in search, recommendations, or personalization. You'll work alongside senior scientists and engineers to develop models and systems that power traditional discovery experiences — such as search ranking, query understanding, and personalized recommendations — built on rich product knowledge graphs and structured metadata. You'll also help extend these foundations into emerging agentic discovery experiences, where AI agents leverage these retrieval and knowledge systems to help customers find and evaluate software solutions. This is a great opportunity to have direct impact on the future of software discovery on AWS Marketplace.
Responsibilities
Design, develop, and deploy AI/ML models for search ranking, query understanding, recommendation, and discovery systems
Develop and improve information retrieval systems that operate over complex product taxonomies, knowledge graphs, and structured/unstructured metadata
Build relevance models that capture nuanced relationships between customer intent, product capabilities, and domain-specific context
Advance both traditional discovery experiences (search, browse, personalized recommendations) and agentic discovery with multi-agent systems
Conduct experiments and A/B tests to measure and improve the relevance and performance of discovery features
Analyze large-scale datasets to identify patterns, generate insights, and inform model development
Collaborate with engineers and product managers to integrate AI/ML solutions into production systems
Stay current with relevant research in information retrieval, knowledge representation, NLP, and recommendation systems, and apply findings to improve our systems
Qualifications
Minimum
Experience programming in Java, C++, Python or related language
PhD in computer science, machine learning, engineering, or related fields
3+ years of building machine learning models or developing algorithms for business application experience
Preferred
Experience with knowledge graphs, entity resolution, or taxonomy-based retrieval systems
Experience with learning-to-rank, semantic search, or neural information retrieval techniques
Experience with deep learning frameworks (PyTorch, TensorFlow) and large-scale data processing (Spark, etc.)
Familiarity with large language models, retrieval-augmented generation, or agentic AI systems
Experience deploying AI/ML models to production at scale
Familiarity with NLP techniques, embeddings, or transformer-based models
Track record of published research or patents in relevant areas