Safety Engineer

ElevenLabs ElevenLabs · AI Frontier · United Kingdom · Engineering & Product

AI Safety Engineer responsible for the deployment and operationalization of automated moderation and guardrail systems across a multimodal space. This role involves building production-grade safety infrastructure, designing APIs, data pipelines, and monitoring systems, and translating research models into production-ready systems. The focus is on end-to-end technical execution of safety systems, from architecture to deployment and monitoring, ensuring robustness, observability, and scalability.

What you'd actually do

  1. Design and build scalable backend infrastructure for content moderation, abuse detection and agents guardrails, deploying AI/ML models into production systems
  2. Architect robust APIs, data pipelines, and service architectures supporting real-time and batch moderation workflows
  3. Implement comprehensive monitoring, alerting, and observability systems; establish SLIs, SLOs, and performance benchmarks
  4. Partner with ML engineers to translate research models into production-ready systems and integrate them across our product suite
  5. Drive technical decisions and contribute vision to the safety roadmap on how the next generation of platform guardrails should be built for scale and precision.

Skills

Required

  • backend software engineering
  • production systems at scale
  • distributed systems
  • APIs
  • data pipelines
  • Python
  • asynchronous Python
  • backend frameworks
  • cloud platforms (AWS/GCP)
  • containerization (Docker/K8s)
  • CI/CD pipelines
  • monitoring tools (Prometheus, Grafana)
  • building observable systems
  • deploying ML/AI systems in production

Nice to have

  • Trust & Safety
  • Content Moderation
  • Integrity engineering
  • MLOps
  • deployment of ML models
  • monitoring of ML models
  • versioning of ML models
  • SQL
  • data analysis tools
  • real-time streaming systems (Kafka, Redis)
  • event-driven architectures
  • React
  • modern frontend frameworks

What the JD emphasized

  • 6+ years of backend software engineering experience building production systems at scale
  • Strong production backend experience
  • Infrastructure & DevOps proficiency
  • Observability mindset with experience in monitoring tools (Prometheus, Grafana) and building observable systems
  • Track record of taking products or systems from 0→1 with measurable impact, including deploying or working alongside ML/AI systems in production

Other signals

  • building production-grade safety infrastructure
  • deploying AI/ML models into production systems
  • content moderation, abuse detection and agents guardrails