Senior AI Security Engineer - Claude Threat Modeling

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

Job summary

Anthropic is seeking a Senior Application Security Engineer to design and operate Claude-powered security systems. You will own end-to-end security tooling and threat modeling for production AI systems.

Work with cross-functional teams to harden architectures, participate in bug bounty efforts, and advance secure design reviews. This role emphasizes hands-on implementation and systems thinking in a fast-moving AI environment.

Qualifications

• Hands-on application and infrastructure security in cloud and containerized environments.
• Production-quality coding in at least one of Python, Go, Rust, or TypeScript.
• Threat-modeling and vulnerability-identification in real systems.
• Ability to operate with high autonomy and ambiguity.
• Clear technical communication with engineers and leadership.

Responsibilities

• Design, build, and operate Claude-powered security systems end-to-end — including analysis, remediation, and threat modeling.
• Lead secure design reviews and threat modeling for novel AI systems.
• Advance a public bug bounty program with automation handling routine triage and root-cause work.
• Partner with Product, Infrastructure, and Research as an embedded security owner.
• Share an on-run rotation including incident response and launch consults for Claude in production.

Skills

AppSec experience

Coding: Python/Go/Rust/TS

Threat modeling

Autonomy & ambiguity

Technical communication

LLM-driven security

Education

Bachelor’s degree in CS or related field

Tools

Cloud & container tech

Security tooling

Job description

Anthropic is seeking a Senior Application Security Engineer to design and operate Claude-powered security systems. You will own end-to-end security tooling and threat modeling for production AI systems.

Work with cross-functional teams to harden architectures, participate in bug bounty efforts, and advance secure design reviews. This role emphasizes hands-on implementation and systems thinking in a fast-moving AI environment.