Software Engineer, AI Safety

About this role

Join OpenAI's Safety Systems team to build infrastructure that detects abuse, prevents misuse, and ensures responsible AI deployment. You'll collaborate with engineers and researchers to develop content moderation systems and monitoring tools that keep users safe while maintaining product integrity.

What you'll do

• Design and maintain anti-abuse and content moderation infrastructure to protect users from harmful behavior
• Collaborate with engineers and researchers to measure and improve AI model alignment using industry-standard and novel techniques
• Diagnose and resolve active platform incidents and build tooling to address root causes of failures
• Work across teams to deploy safety features while balancing capabilities and risk mitigation
• Develop classifiers and machine learning infrastructure for safety monitoring
• Implement solutions that prevent unwanted behavior without degrading user experience

What they're looking for

• Production service development and scaling
• Python or modern languages (C++, Rust, Go)
• Kubernetes, Terraform, and cloud infrastructure (Azure)
• Debugging and incident response
• Machine learning model deployment
• Content safety, fraud, or abuse prevention experience
• Project management and self-direction
• Risk assessment and mitigation strategies