jobs

Red Team Engineer, Safeguards

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers,

Company

Anthropic

Location

Remote-Friendly (Travel Required); San Francisco, CA

Status

Open

Posted

2026-07-10T22:50:56+00:00

Anthropic's Safeguards team is hiring a red team engineer to attack the company's own AI products and find weaknesses before malicious actors do. The role spans penetration testing, model jailbreaking, prompt-injection checks on large agentic workflows, and multi-stage attacks that chain several vectors, along with building automated testing frameworks and detection metrics. Requirements include red teaming or application security experience, web security tooling such as Burp Suite and Metasploit, custom LLM testing automation, and public work like CVEs, write-ups or bug bounty disclosures.