Staff Software Engineer - AI Safety & Safeguards

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

Benefits offered by this job

Equity donation matching

Flexible hours

Office space

Vacation & parental leave

Job summary

Anthropic is hiring software engineers to build safety and oversight mechanisms for AI systems. As a member of the Safeguards team, you will monitor models, prevent misuse, and ensure user wellbeing with scalable defenses and automated enforcement actions.

You will contribute to detecting unwanted model behaviors, surface abuse patterns to research teams, and strengthen safeguards across the stack using Python and TypeScript.

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering or comparable experience.
• Proficiency in Python and Typescript.
• 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 take automated enforcement actions, surfacing results on internal dashboards for analysts.
• Build abuse detection mechanisms and infrastructure.
• Surface abuse patterns to research teams to harden models during training.
• Build robust and reliable multi-layered defenses for real‑time improvement of safety mechanisms that work at scale.

Skills

Python

Typescript

Cross-stack development

Communication

Education

Bachelor’s degree in Computer Science or Software Engineering

Job description

Anthropic is hiring software engineers to build safety and oversight mechanisms for AI systems. As a member of the Safeguards team, you will monitor models, prevent misuse, and ensure user wellbeing with scalable defenses and automated enforcement actions.

You will contribute to detecting unwanted model behaviors, surface abuse patterns to research teams, and strengthen safeguards across the stack using Python and TypeScript.