Safeguards Software Engineer – AI Safety & Abuse Detection

Anthropic Limited; San Francisco (CA); Hybrid; USD 320,000 - 485,000; Full time

Benefits offered by this job

Health insurance

Job summary

Anthropic Limited is seeking software engineers for the Safeguards team to build safety and oversight mechanisms for AI systems. You will monitor models, prevent misuse, and ensure user well-being across our platform.

Collaborate with researchers, policy experts, and engineers to surface abuse signals, enforce terms of service, and strengthen defenses. This role offers growth potential within a fast-growing AI safety organization.

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering or comparable professional experience.
• Proficiency in Python, Java, or similar languages.
• Ability to work across the stack.
• Strong communication skills to explain complex concepts.

Responsibilities

• Develop monitoring systems to detect unwanted API partner behaviors and surface results for analyst review.
• Build abuse detection mechanisms and supporting infrastructure.
• Share abuse patterns with research teams to harden models at training.
• Create multi-layered defenses to improve real-time safety at scale.

Skills

Python

Java

Cross-stack development

Communication skills

Education

Bachelor’s degree in Computer Science or Software Engineering

Job description

Anthropic Limited is seeking software engineers for the Safeguards team to build safety and oversight mechanisms for AI systems. You will monitor models, prevent misuse, and ensure user well-being across our platform.

Collaborate with researchers, policy experts, and engineers to surface abuse signals, enforce terms of service, and strengthen defenses. This role offers growth potential within a fast-growing AI safety organization.