Mercor is seeking AI Safety Experts to test conversational AI systems from a remote location. You will work on jailbreaks, prompt injections, and bias detection, focusing on safety and reliability.
You should be fluent in English and Kannada, with prior red-teaming experience in AI or cybersecurity. This contract role offers $20–$22 per hour and flexible remote collaboration. You will collaborate with researchers, document findings, and contribute to playbooks and client reports.
#J-18808-LjbffrAI Adversarial Safety Lead (English & Kannada) Remote in Remote at Unknown Company
This position is listed as contract and able to be worked remotely.