Safety Engineer (Back-End Leaning)

Overview

Build and operate the automated moderation, abuse detection and guardrail systems that keep ElevenLabs' AI products safe, with a backend-leaning engineering focus.

What you'll do

• Design, develop, and scale automated moderation systems, abuse detection capabilities, and guardrails for AI agents across ElevenLabs' products.
• Partner closely with the Investigations team to identify emerging abuse patterns, understand evolving threats, and continuously improve existing safety systems, detection mechanisms, and guardrails.
• Build and maintain a growing ecosystem of internal safety services, taking ownership of their architecture, deployment, reliability, monitoring, and ongoing operation.
• Partner closely with ML engineers to deploy and integrate fine-tuned and proprietary ML models into production safety systems, ensuring they operate reliably and efficiently at scale.
• Develop backend services, APIs, internal tools, and user-facing interfaces that enable effective moderation, safety operations, and policy enforcement.
• Work closely with Product, Legal, and Safety Policy teams to translate business, regulatory, and policy requirements into scalable engineering solutions.
• Understand and navigate the tradeoffs between product growth, user experience, and platform safety.
• Translate legal and regulatory requirements into practical, scalable safety systems.
• Collaborate on how safety policies are implemented technically, while helping inform policy decisions through an understanding of engineering capabilities and constraints.
• Contribute to architectural decisions and help define how the safety infrastructure evolves as products, users, and safety challenges grow.

What you'll need

• 5+ years of software engineering experience building and operating production systems.
• Strong backend engineering experience, including designing APIs, working with databases, and building scalable services.
• Proficiency in Python and experience with modern backend frameworks.
• Experience building and maintaining distributed systems and cloud-based applications.
• Comfortable owning systems end to end, from technical design and implementation through deployment, monitoring, and ongoing maintenance.
• Experience working across different parts of the stack, with the ability to build internal tools or frontend interfaces when needed.
• Strong problem-solving skills and an ability to navigate ambiguous requirements and make pragmatic engineering decisions.
• Ability to collaborate effectively with engineers and non-technical stakeholders across different functions.

Nice to have

• Experience building Trust & Safety, content moderation, fraud detection, or abuse prevention systems.
• Experience building guardrails or safety infrastructure for AI agents and LLM-based applications.
• Experience deploying and integrating ML models into production applications.
• Familiarity with Kubernetes, Docker, CI/CD pipelines, and cloud infrastructure (AWS/GCP).
• Experience with monitoring and observability tools such as Prometheus and Grafana.
• Experience with React or other modern frontend frameworks.
• Experience with real-time data processing, event-driven architectures, or technologies such as Kafka and Redis.

Details

• Remote role that can be executed globally.
• Optional work from ElevenLabs offices in London, New York, San Francisco, and Warsaw.