LLM Post Training Intern
OtherTextPrompt Response Writing SFT
As an LLM Post Training Intern at Ethara AI, I performed high-quality data annotation and response evaluation to improve LLM outputs. I ensured model accuracy, reasoning quality, and instruction alignment through precise annotation and human feedback evaluation. I contributed to supervised fine-tuning and created evaluation guidelines for prompt-response pairs in real-world contexts.
• Conducted data annotation and prompt-response evaluation for Large Language Models.
• Applied SFT support and human feedback evaluation to enhance model performance.
• Designed edge cases and comprehensive evaluation scenarios for model robustness.
• Focused on accuracy, factual correctness, and reduction of model hallucinations.
As an LLM Post Training Intern at Ethara AI, I performed high-quality data annotation and response evaluation to improve LLM outputs. I ensured model accuracy, reasoning quality, and instruction alignment through precise annotation and human feedback evaluation. I contributed to supervised fine-tuning and created evaluation guidelines for prompt-response pairs in real-world contexts. • Conducted data annotation and prompt-response evaluation for Large Language Models. • Applied SFT support and human feedback evaluation to enhance model performance. • Designed edge cases and comprehensive evaluation scenarios for model robustness. • Focused on accuracy, factual correctness, and reduction of model hallucinations.
2026 - 2026