Staff Software Engineer, AI Safety & Safeguards

Jobs in JS; Seattle (WA); Hybrid; USD 320,000 - 485,000; Full time

Job summary

Anthropic is seeking software engineers to build safety and oversight mechanisms for AI systems. As part of the Safeguards team, you will monitor models, prevent misuse, and enforce our terms of service while developing scalable defenses and detection systems.

The role focuses on detecting unwanted model behaviors, preventing disallowed use, and surfacing abuse patterns for internal review. A strong CS foundation and experience with Python/TypeScript are essential.

Qualifications

• Bachelor’s degree in CS, SE or equivalent is required.
• Proficiency in Python and TypeScript is required.
• 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 in dashboards.
• Build abuse detection mechanisms and infrastructure.
• Surface abuse patterns to research teams to harden models at training.
• Develop multi-layered defenses for real-time safety improvements at scale.

Skills

Python

TypeScript

Across the stack

Strong communication

Education

Bachelor’s degree in Computer Science or equivalent

Job description

Anthropic is seeking software engineers to build safety and oversight mechanisms for AI systems. As part of the Safeguards team, you will monitor models, prevent misuse, and enforce our terms of service while developing scalable defenses and detection systems.

The role focuses on detecting unwanted model behaviors, preventing disallowed use, and surfacing abuse patterns for internal review. A strong CS foundation and experience with Python/TypeScript are essential.