Red Team Engineer, Safeguards

Aicompliance; San Francisco (CA); Remote; USD 320.000 - 405.000; Vollzeit

Zusammenfassung

Anthropic in San Francisco, CA is seeking a Safeguards Engineer to conduct adversarial testing across deployed AI products and capabilities. The role is remote-friendly with travel required, offering a compensation range of $320,000 to $405,000 per year.

The successful candidate will identify vulnerabilities, craft attack scenarios, and collaborate with product and safety teams to harden systems while maintaining rigorous compliance with AI safety practices.

Aufgaben

• Identify vulnerabilities in AI systems through adversarial testing.
• Develop attack scenarios and test plans.
• Collaborate with product and safety teams to implement mitigations.

Jobbeschreibung

Anthropic Remote-Friendly (Travel Required) | San Francisco, CA Remote $320,000 - $405,000

Safeguards role using adversarial testing to uncover vulnerabilities across Anthropic's deployed AI products and advanced AI capabilities.

Independent aggregation of a publicly posted role. AI Compliance Index is not affiliated with, endorsed by, or recruiting for Anthropic. All applications happen on the employer's own site; listings may expire.