Staff+ Software Engineer, Safeguards

Overview

Software engineer on Anthropic’s Safeguards team, building safety and oversight mechanisms for AI systems.

What you'll do

• Develop monitoring systems to detect unwanted behaviors from API partners.
• Apply automated enforcement actions and present findings in internal dashboards for analyst review.
• Build abuse detection mechanisms and supporting infrastructure.
• Surface abuse patterns to research teams to improve models at the training stage.
• Create robust multi-layered defenses for real-time safety improvements at scale.
• Build systems to detect unwanted model behaviors and prevent disallowed use.

What you'll need

• Proficiency in Python.
• Proficiency in Typescript.
• Ability to work across the stack.
• Strong communication skills to explain complex technical concepts to non-technical stakeholders.
• Bachelor’s degree in Computer Science, Software Engineering, or comparable experience.

Details

• Location-based hybrid policy: expected to be in an office at least 25% of the time.
• Visa sponsorship is available (not guaranteed for every role/candidate).
• Annual compensation range: $320,000–$485,000 USD.