New opportunity

AI Red Team Engineer

White Circle · New York; San Francisco

About this role

Perform adversarial testing of LLM-powered systems, automate attacks and tests in Python, build an internal attack library and regression tests, and produce clear, reproducible reports and evidence to support customer demos and security reviews.

Skills for this role

LLMsPromptsSystem instructionsRAGAI agentsTool/function callingPrompt injectionJailbreaksSensitive-data leakageToken-cost abusePythonAPI testingWeb app testingSaaS product testingQA automationApplication security (AppSec)Penetration testingBug bountyBurp SuitePostmanPlaywrightpytestLangChainLangGraphLlamaIndexOWASP LLM Top 10OWASP Web Top 10MITRE ATLASEval pipelinesRegression testing''CI-friendly security tests''Security reporting''Trust &s