Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
Handshake AI is seeking an AI Red Teamer (LLM Generalist) to stress-test large language models by crafting adversarial prompts, exploring jailbreak and evasion techniques, and evaluating model outputs against harm taxonomies. You will work across risk categories including safety, security, and regulatory compliance, collaborating with engineers and researchers.
The role is remote (USA) with 40 hours per week, paid hourly through TCWGlobal.
Handshake AI is seeking an AI Red Teamer (LLM Generalist) to stress-test large language models by crafting adversarial prompts, exploring jailbreak and evasion techniques, and evaluating model outputs against harm taxonomies. You will work across risk categories including safety, security, and regulatory compliance, collaborating with engineers and researchers.
The role is remote (USA) with 40 hours per week, paid hourly through TCWGlobal.