Become a pivotal force in AI safety as a Red Teaming Specialist. Work fully remote with a global team, pushing the limits of generative AI to expose vulnerabilities and enhance security. In this role, you will engage in cutting-edge Red Teaming for AI and Large Language Models (LLMs). Seeking innovative and resourceful individuals who thrive in fast-paced settings, you will collaborate with expert teams while honing skills in identifying vulnerabilities. Your contributions will play a vital role in shaping the future of secure AI applications. Key Responsibilities: Complete extensive training on AI, LLMs, and Red Teaming Craft clever prompts to challenge AI filters Collaborate with language and QA specialists on projects Assist data scientists in conducting automated model attacks Stay updated on evolving LLM capabilities and vulnerabilities Requirements: Bachelor''''s or Associate''''s degree with 1 year industry experience Advanced proficiency in English and Simplified Chinese Strong understanding of grammar and syntax Must handle potentially sensitive material Eagerness to learn about emerging AI technologies Utilize your creativity and language skills to enhance the reliability of AI systems and contribute to groundbreaking security practices. #J-18808-Ljbffr
Job Title
Remote Red Teaming Specialist for AI Safety and Security