Machine Learning Engineer, Personalization

About the Role

The Machine Learning Engineer, Personalization at Spotify plays a crucial role in enhancing the listener experience by making content discovery easier and more enjoyable. You will join the Personalization team's Minesweeper squad, which focuses on generating Human Understandable Language Knowledge to enrich audio content understanding. This involves applying advanced AI and ML techniques, including Large Language Models (LLMs), to music, podcasts, and audiobooks, and building scalable systems to distribute this knowledge globally.

This is a unique opportunity to directly contribute to the future of Spotify's content enrichment and recommendation systems, impacting hundreds of millions of users worldwide. You'll work in a collaborative, cross-functional environment alongside Data Engineers, Backend Engineers, and researchers, developing your skills in large-scale ML engineering within a motivated and supportive team.

What You'll Do

• Utilize in-house and third-party LLMs to tackle complex language understanding challenges.
• Employ advanced techniques such as fine-tuning and Retrieval-Augmented Generation (RAG) to continuously improve model performance.
• Contribute hands-on to the design, building, evaluation, deployment, and refinement of Spotify's product features through ML development.
• Help drive optimization, rigorous testing, and tooling enhancements to elevate the quality of content enrichment assets.
• Collaborate effectively with cross-functional teams including other Machine Learning Engineers, data and backend engineers, and key stakeholders from tech research, data science, and product development.
• Actively participate in Spotify's AI Foundation’s ML community, contributing to and leveraging existing platforms and systems.
• Perform comprehensive data analysis to establish performance baselines and inform critical product decisions.
• Stay abreast of the latest advancements in machine learning algorithms and techniques to ensure cutting-edge solutions.

Who You Are

• You possess a robust background in machine learning, with particular expertise and hands-on experience in Large Language Models.
• You have demonstrated professional experience in applied machine learning within a product-driven environment.
• You are highly proficient in programming languages like Python (required), Scala, or Java, and SQL.
• You have extensive experience working with cloud platforms such as Google Cloud Platform (GCP) or Amazon Web Services (AWS).
• You have practical experience implementing or prototyping machine learning systems at scale.
• You are skilled in architecting data pipelines and are self-sufficient in sourcing and preparing data for model building and evaluation, utilizing tools like Dataflow, Apache Beam, or Spark.
• You are committed to agile software processes, data-driven development, ensuring reliability, and conducting disciplined experimentation.
• You have experience with and a passion for fostering collaborative team environments.
• You are proficient with PyTorch, TensorFlow, and/or other scalable Machine Learning frameworks.
• Experience with Ray or TFX is considered a valuable asset.
• Bonus points if you have experience architecting near real-time data pipelines.

Key skills/competency

• Machine Learning
• Large Language Models (LLMs)
• Python
• Cloud Platforms (GCP/AWS)
• Data Pipelines
• PyTorch
• TensorFlow
• Apache Spark
• Data Analysis
• Scalable Systems