Join Amazon Music's Catalog Quality team as a Machine Learning Engineer. We are dedicated to ensuring accurate, comprehensive, and enriched music metadata across the Amazon Music catalog. Our team leverages advanced technologies like LLMs, computer vision, and NLP to maintain and enhance metadata quality in real-time.

Our core mission is to deliver high-quality, dynamically validated, and enriched catalog metadata with minimal latency throughout the Amazon Music experience. We automate the identification and correction of metadata inconsistencies, including misattributed tracks, duplicate content, incorrect artist details, and incomplete album information. Additionally, we provide internal teams with robust tools for continuous catalog integrity improvement at scale.

Design, develop, and manage scalable machine learning pipelines and online serving systems. Collaborate closely with applied scientists to refine ML model performance and implement end-to-end solutions, from initial experimentation to production deployment. Champion technological advancements and drive ongoing innovation in ML infrastructure across the sponsored products organization. Partner with product managers, scientists, and fellow engineers to deliver optimal customer-focused products. Foster strong working relationships with complementary disciplines, including Product, Science, and Engineering, to ensure customer-centric outcomes. Contribute to operational excellence by monitoring, troubleshooting, and supporting high-volume, low-latency systems.

Possess at least 3 years of professional software development experience, excluding internships. Have 2+ years of experience in designing or architecting new and existing systems, including applying design patterns and ensuring reliability and scalability. Demonstrate experience working with PyTorch or JAX software. Accumulate 2+ years of experience building large-scale machine learning infrastructure for applications such as online recommendation, ad ranking, personalization, or search. Preferred qualifications include 3+ years in the full software development life cycle (coding standards, code reviews, source control, build processes, testing, operations) and a Master's degree in Computer Science or a related field. Familiarity with Machine Learning and LLM fundamentals, including transformer architecture, training/inference lifecycles, and optimization techniques is also highly valued.