Tech and design

Red Team Engineer, Safeguards

AnthropicSan Francisco, CA

• Pay$320,000–405,000 per year
• WhereSan Francisco, CA
• TermsFull-time
• PerksVisa sponsorship
• Skills and toolsPenetration testing, Model jailbreaking, Prompt injection, Web application security, Burp Suite, Metasploit, Custom scripting frameworks, LLM-specific testing frameworks, Adversarial machine learning, API security
• You’ll needBachelor's degree or equivalent experience, Public body of security work
• ReferenceRef. 6078
• In the paper untilThu 19 Nov

About the job

Hybrid, at least 25% in office. Adversarial testing of AI products, including model jailbreaking, prompt injection, and web application security. Bachelor’s degree or equivalent experience; public body of security work. Visa sponsorship available.

This is our short summary. Read the full posting on boards.greenhouse.io.

Found on boards.greenhouse.io. Not placed by the employer; applications go to the original posting.