Staff Software Engineer, AI Safety & Abuse Defenses

Anthropic; New York (NY); Hybrid; USD 320,000 - 485,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching

Vacation and parental leave

Flexible working hours

Office space

Job summary

Anthropic is seeking software engineers to build safety and oversight mechanisms for AI systems. You will monitor models, prevent misuse, and enforce terms of service while upholding safety and transparency.

The role emphasizes cross-stack work, strong communication, and collaboration with researchers and policy teams. Responsibilities include developing monitoring systems, building abuse detection, surfacing patterns to improve models, and creating scalable defenses for real-time safety.

Qualifications

• Bachelor’s degree or equivalent in CS/Software Engineering or related field.
• Proficiency in Python and Typescript.
• Ability to work across the stack and communicate complex concepts clearly.

Responsibilities

• Develop monitoring systems to detect unwanted behaviors from API partners and surface results for review
• Build abuse detection mechanisms and infrastructure
• Surface abuse patterns to research teams to harden models at training
• Build scalable defenses for real-time safety improvements

Skills

Python

Typescript

Across the stack

Communication

Education

Bachelor’s degree in Computer Science / Software Engineering or comparable experience

Job description

Anthropic is seeking software engineers to build safety and oversight mechanisms for AI systems. You will monitor models, prevent misuse, and enforce terms of service while upholding safety and transparency.

The role emphasizes cross-stack work, strong communication, and collaboration with researchers and policy teams. Responsibilities include developing monitoring systems, building abuse detection, surfacing patterns to improve models, and creating scalable defenses for real-time safety.