Mission Statement
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.
About the Team
Safe-and-Sound is the centralized Safety team within the AI Foundations Studio in Personalization. We build machine learning systems that help ensure Spotify experiences and recommendations are safe, responsible, and enjoyable across core surfaces like Home, Search, as well as newer generative AI experiences.
We partner closely with Tech Research, Trust & Safety, and Content Platform to develop new approaches in areas like synthetic data, fairness, and responsible AI. Our focus is on building scalable, high-impact systems that support both today’s products and the next generation of AI-driven experiences.
What You'll Do
Design, build, and improve machine learning systems that power safety across personalization surfaces such as recommendations, search, and emerging AI experiences
Contribute to the platformization of safety systems, enabling scalable and reusable solutions across teams
Develop and operate high-throughput, low-latency backend services powered by ML models
Partner with Product, Trust & Safety, and Content Platform to translate safety needs into practical technical solutions
Work on both traditional ML models and generative AI systems, including integrating third-party and in-house foundational models
Contribute to evaluation frameworks, including labeling strategies, ground truth creation, and model validation approaches
Collaborate with foundational model teams to embed safety into LLM-based and agent-driven experiences
Use metrics and experimentation to continuously improve system performance, safety outcomes, and user experience
Who You Are
You are experienced in building and deploying machine learning systems in production environments
You have hands-on experience with both traditional ML approaches and newer generative AI techniques
You have worked with scalable backend systems that require reliability, low latency, and high availability
You understand how to apply ML solutions to real-world product challenges, ideally in consumer-facing products
You have experience with model evaluation approaches such as labeling workflows, red-teaming, or ground truth data generation
You are comfortable working across disciplines, collaborating with product managers, researchers, and policy partners
You care deeply about building safe, responsible, and inclusive user experiences
You bring a thoughtful, metrics-driven approach to problem solving and decision-making
Where You'll Be
This role is based in New York or Boston
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
