Staff+ Software Engineer, Safeguards

What this role involves

Anthropic is hiring a Staff Software Engineer for the Safeguards team to develop monitoring systems and abuse detection mechanisms for AI systems. The role requires proficiency in Python and TypeScript, and involves building automated enforcement and internal dashboards for safety oversight. Preferred experience includes trust and safety detection for AI/ML, prompt engineering, and adversarial input handling.

Skills this posting asks for

• python
• typescript
• abuse detection
• trust and safety
• machine learning
• prompt engineering
• adversarial inputs
• internal tooling

Requirements

• Level: staff
• Remote policy: hybrid
• Visa sponsorship: yes

From the employer’s posting

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, en…