Senior Machine Learning Engineer, Personalization, Magenta

About this role

The Personalization team makes deciding what to play next easier and more enjoyable for every listener. From Blend to Discover Weekly, we’re behind some of Spotify’s most-loved features. We built them by understanding the world of music and podcasts better than anyone else. Join us and you’ll keep millions of users listening by making great recommendations to each and every one of them. The Personalization team at Spotify makes deciding what to listen to next feel effortless for hundreds of millions of users — from Discover Weekly to our newest AI-powered experiences. We’re now building conversational AI capabilities that let users interact with Spotify in natural language. You’ll join a squad working at the core of this space, shaping how users discover and engage with audio through intelligent, responsive systems.

Design and ship production-grade machine learning systems powering conversational and agentic AI experiences

Build systems that interpret user intent, manage context across multi-turn interactions, and handle ambiguity reliably at scale

Develop and evolve agentic workflows including memory, context management, and multi-step tool orchestration

Create evaluation frameworks, including LLM-as-judge pipelines, to measure quality and guide iteration

Partner closely with product, engineering, and design to deliver seamless, user-facing experiences

Balance experimentation with production rigor, ensuring performance, latency, and reliability at Spotify scale

Continuously improve agent behavior through tight feedback loops between evaluation and real-world usage You have 5+ years of experience building and shipping machine learning systems in production environments

You are experienced with large language models and have worked on real-world applications beyond experimentation; shipped and maintained large scale systems with LLMs

You have a deep understanding of challenges in conversational or agentic systems, such as context handling and multi-step reasoning

You know how to evaluate ML systems rigorously and have experience designing metrics or evaluation pipelines

You are comfortable debugging complex interactions between models, tools, and system constraints like latency

You care about building reliable, scalable systems that deliver high-quality user experiences

You enjoy working cross-functionally and contributing to a collaborative, inclusive team environment This role is based in New York

We offer you the flexibility to work where you work best! There will be some in person meetings, but still allows for flexibility to work from home