AI Language Evaluation Specialist
Text
As an AI Language Evaluation Specialist, I evaluated and improved LLM-generated responses to enhance model reasoning, safety, and contextual relevance. I designed complex prompts and multi-turn conversation flows for fine-tuning large language models in Korean, English, and Japanese. I carried out adversarial testing and produced step-by-step assistant outputs to raise dataset quality and safety. • Evaluated and ranked AI-generated responses to increase model accuracy. • Designed realistic conversation scenarios for model refinement. • Conducted adversarial red-teaming to detect hallucinations and biases. • Delivered QA-verified datasets adhering to strict alignment protocols.
As an AI Language Evaluation Specialist, I evaluated and improved LLM-generated responses to enhance model reasoning, safety, and contextual relevance. I designed complex prompts and multi-turn conversation flows for fine-tuning large language models in Korean, English, and Japanese. I carried out adversarial testing and produced step-by-step assistant outputs to raise dataset quality and safety. • Evaluated and ranked AI-generated responses to increase model accuracy. • Designed realistic conversation scenarios for model refinement. • Conducted adversarial red-teaming to detect hallucinations and biases. • Delivered QA-verified datasets adhering to strict alignment protocols.
2025 - Present