Staff Software Engineer, AI Safety & Safeguards

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

Job summary

Anthropic is seeking a Staff+ Software Engineer, Account Creation to help build safety and oversight mechanisms for our AI systems. You will work on monitoring models, preventing misuse, and ensuring user well-being across the stack.

This role emphasizes building multi-layered defenses and surfacing abuse patterns to researchers to harden models, enabling real-time safety at scale. Hybrid work is expected, with visa sponsorship available where applicable.

Qualifications

• Bachelor's degree in Computer Science or related field required.
• Proficiency in Python and Typescript.
• Ability to work across the stack and communicate clearly.
• Experience with safety, AI/ML systems is a plus.

Responsibilities

• Develop monitoring systems to detect unwanted behaviors in API partners.
• Build abuse detection mechanisms and infrastructure.
• Surface abuse patterns to research teams to harden models.
• Contribute to real-time safety defenses at scale.

Education

Bachelor's degree in Computer Science or related field

Tools

Python

Typescript

Job description

Anthropic is seeking a Staff+ Software Engineer, Account Creation to help build safety and oversight mechanisms for our AI systems. You will work on monitoring models, preventing misuse, and ensuring user well-being across the stack.

This role emphasizes building multi-layered defenses and surfacing abuse patterns to researchers to harden models, enabling real-time safety at scale. Hybrid work is expected, with visa sponsorship available where applicable.