AI Jailbreak And Prompt-Injection Security Expert
OpenTrain AI · US
$187k/yrPosted 5h agoIT
Position summary
The Work You will assess how AI systems respond to adversarial prompts and security threats. The work combines hands-on testing with clear reports and recommendations for improving model safety. You will create repeatable evaluation methods, maintain regression tests, and explain technical findings to both technical and non-technical audiences. Design tests for jailbreaks, prompt injection, tool-use abuse, and other unsafe model behaviors. Develop multi-turn and cross-domain strategies that unc…
This is the summary the employer released for listing. Full requirements, schedule and benefits appear on the employer's application page — continue below to read everything and apply.