Korean-English AI Trainer / Outlier.ai
OtherText
As a Korean-English AI Trainer at Outlier.ai, I conducted quality evaluations of AI-generated text content. I ensured that outputs met standards for accuracy, coherence, and compliance with project guidelines. I optimized large language model (LLM) performance with reinforcement learning from human feedback (RLHF) techniques.
• Performed hands-on evaluation and rating of diverse AI-generated texts.
• Applied RLHF strategies to improve LLM effectiveness.
• Maintained documentation regarding content quality and labeling standards.
• Collaborated remotely on cross-functional project teams.
As a Korean-English AI Trainer at Outlier.ai, I conducted quality evaluations of AI-generated text content. I ensured that outputs met standards for accuracy, coherence, and compliance with project guidelines. I optimized large language model (LLM) performance with reinforcement learning from human feedback (RLHF) techniques. • Performed hands-on evaluation and rating of diverse AI-generated texts. • Applied RLHF strategies to improve LLM effectiveness. • Maintained documentation regarding content quality and labeling standards. • Collaborated remotely on cross-functional project teams.
2024 - Present