Machine Learning Engineer - Policy & Safety

We design Spotify's consumer experience,end to end, moment to moment, across every screen, platform, and partner integration. Our mission is to make listening feel effortless, personal, and joyful for billions of users around the world.

The Policy & Safety team sits within the Content Platform domain and builds the systems that keep Spotify safe and trustworthy at scale. We own the infrastructure behind content moderation, including detection models, policy enforcement systems, compliance pipelines, and the safety-by-default platform.

Responsibilities

• Build and scale machine learning systems for proactive content detection, classification, and pre-publish safety scanning
• Design and implement policy evaluation frameworks, including standardized datasets, offline and online metrics, and continuous improvement loops
• Develop multimodal models that combine text, audio, image, and video signals for safety and policy enforcement
• Architect feedback loops that turn human reviewer input into structured training data for continuous model improvement
• Translate regulatory requirements into scalable ML system designs
• Partner with cross-functional teams across Trust & Safety, Legal, Public Affairs, and Product to deliver safe user experiences
• Drive technical direction in ambiguous problem spaces and contribute to long-term platform architecture
• Mentor and support other machine learning engineers, helping raise the bar across the team

Requirements

• Experience building and shipping production-grade machine learning systems at scale
• Strong expertise in ML evaluation, including dataset design, metrics, and model performance monitoring
• Work experience with multimodal machine learning systems across text, audio, image, or video domains
• Experience with human-in-the-loop systems, active learning, or feedback-driven model improvement
• Ability to translate complex requirements into technical solutions, including regulatory or policy constraints
• Experience working across teams and influencing technical direction in large-scale systems
• Comfortable navigating ambiguity and making thoughtful decisions that balance speed, quality, and risk
• Clear communication and effective collaboration with both technical and non-technical stakeholders