AI Training Specialist (Contract)
OtherTextRLHF
As an AI Training Specialist, I provided high-quality human feedback for the optimization of large language models. My primary tasks included ranking and rewriting model responses to improve safety, truthfulness, and helpfulness. I also developed complex prompts and participated in reinforcement learning from human feedback (RLHF) projects.
• Performed rigorous fact-checking against academic and primary sources.
• Identified and mitigated hallucinations in AI-generated content.
• Crafted multi-turn prompts for testing model boundaries in coding, creative writing, and logical reasoning.
• Collaborated to achieve better LLM adherence to stylistic and formatting constraints.
As an AI Training Specialist, I provided high-quality human feedback for the optimization of large language models. My primary tasks included ranking and rewriting model responses to improve safety, truthfulness, and helpfulness. I also developed complex prompts and participated in reinforcement learning from human feedback (RLHF) projects. • Performed rigorous fact-checking against academic and primary sources. • Identified and mitigated hallucinations in AI-generated content. • Crafted multi-turn prompts for testing model boundaries in coding, creative writing, and logical reasoning. • Collaborated to achieve better LLM adherence to stylistic and formatting constraints.
2023 - Present