Staff AI Safeguards Engineer — Safety & Abuse Detection

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

Job summary

Anthropic Limited in New York is seeking software engineers for the Safeguards team to build safety and oversight mechanisms for our AI systems. As a software engineer on this team, you will monitor models, prevent misuse, and ensure user well-being through robust detection and enforcement tools.

We have multiple teams within Safeguards; placement occurs after interviews to match interests and organizational needs.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering or comparable professional experience.
• Proficiency in at least one programming language such as Python, Java, etc.
• Ability to work across the stack.
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders.

Responsibilities

• Develop monitoring systems to detect unwanted behaviors from API partners and surface in dashboards for analysis.
• Build abuse detection mechanisms and infrastructure.
• Surface abuse patterns to research teams to harden models at training stage.
• Build robust, multi-layered defenses for real-time safety improvements at scale.

Skills

Python

Java

Across the stack

Strong communication

Education

Bachelor's degree in CS/Software Eng

Job description

Anthropic Limited in New York is seeking software engineers for the Safeguards team to build safety and oversight mechanisms for our AI systems. As a software engineer on this team, you will monitor models, prevent misuse, and ensure user well-being through robust detection and enforcement tools.

We have multiple teams within Safeguards; placement occurs after interviews to match interests and organizational needs.