Staff Software Engineer - AI Safety & Safeguards

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

Job summary

Anthropic Limited is seeking a Software Engineer to join the Safeguards team and help build safety and oversight mechanisms for our AI systems. You will monitor models, prevent misuse, and enforce terms of service while deploying scalable, distributed infrastructure.

You will lead multi-month projects, deploy monitoring across clouds, and work with security, privacy, and legal teams to ship reliable, safe AI platform features in a collaborative environment.

Qualifications

• Bachelor’s degree in CS or related field.
• Experience with distributed systems and cloud infra.
• Proficiency in Python and IaC concepts.
• Familiarity with AI safety or model monitoring is a plus.

Responsibilities

• Lead multi-month infrastructure projects from scope to production.
• Develop monitoring to detect unwanted model behaviors and surface findings for review.
• Deploy monitoring across multiple clouds with consistent pipelines and observability.
• Hardening sandboxed runtimes with isolation and access controls.
• Manage cost and capacity for large volumes of agent work and meet SLOs.
• Collaborate with researchers, security, privacy, and legal teams to ship safe features.

Skills

Python

Distributed Systems

Infrastructure as Code

Cloud Providers

LLM Safety

Strong Communication

Education

Bachelor’s degree

Job description

Anthropic Limited is seeking a Software Engineer to join the Safeguards team and help build safety and oversight mechanisms for our AI systems. You will monitor models, prevent misuse, and enforce terms of service while deploying scalable, distributed infrastructure.

You will lead multi-month projects, deploy monitoring across clouds, and work with security, privacy, and legal teams to ship reliable, safe AI platform features in a collaborative environment.