Staff Software Engineer, AI Safety & Safeguards

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

Job summary

Anthropic is seeking software engineers to help build safety and oversight mechanisms for our AI systems. As a software engineer on the Safeguards team, you will monitor models, prevent misuse, and ensure user well‑being, applying your technical skills to uphold safety, transparency, and oversight while enforcing our terms of service.

The role requires a Bachelor’s degree in CS or related field, proficiency in Python and TypeScript, and the ability to work across the stack.

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering or comparable.
• Proficiency in Python and TypeScript.
• Ability to work across the stack and communicate complex ideas clearly.

Responsibilities

• Develop monitoring systems to detect unwanted model behaviors and surface findings for analysts.
• Build abuse detection mechanisms and infrastructure.
• Surface abuse patterns to researchers to harden models at the training stage.
• Contribute to multi-layered defenses for real-time safety improvements at scale.

Skills

Python

TypeScript

Communication

Across the stack

Education

Bachelor’s degree in CS or related field

Job description

Anthropic is seeking software engineers to help build safety and oversight mechanisms for our AI systems. As a software engineer on the Safeguards team, you will monitor models, prevent misuse, and ensure user well‑being, applying your technical skills to uphold safety, transparency, and oversight while enforcing our terms of service.

The role requires a Bachelor’s degree in CS or related field, proficiency in Python and TypeScript, and the ability to work across the stack.