Safety Engineer (Backend Leaning)
Core
Design, develop, and scale automated moderation systems, abuse detection capabilities, and guardrails for AI agents across ElevenLabs' products.
Role type
Senior backend safety engineer (AI safety systems)
Builds
Automated moderation systems, abuse detection capabilities, guardrails, and internal safety services
Domain
AI safety, Trust & Safety, backend infrastructure
Deliverable
production ML models
Required skills
Python, backend engineering, distributed systems, cloud infrastructure, API design, database management, system ownership, problem-solving
Preferred skills
Trust & Safety systems, AI agent guardrails, ML model deployment, Kubernetes, Docker, CI/CD, Prometheus, Grafana, React, Kafka, Redis
Technologies
Python, Kubernetes, Docker, AWS/GCP, Prometheus, Grafana, React, Kafka, Redis
Responsibilities
Design and scale automated moderation systems; Partner with Investigations to identify emerging abuse patterns; Build and maintain internal safety services infrastructure; Deploy and integrate fine-tuned ML models into production; Develop backend services, APIs, and user-facing interfaces for safety operations; Collaborate with Product, Legal, and Safety Policy teams to translate requirements into engineering solutions
Seniority
Senior, hands-on IC
