LLM Post Training Intern
OtherText
I performed high-quality data annotation and response evaluation to improve Large Language Model (LLM) outputs. I applied post-training evaluation techniques to ensure consistency and factual correctness in model responses. I designed and refined prompt-response pairs and evaluation guidelines for diverse scenarios.
• Conducted supervised fine-tuning (SFT) support and human feedback evaluation tasks.
• Focused on improving LLM reasoning, accuracy, and instruction alignment.
• Used the MultiMango platform for data labeling and evaluation.
• Helped reduce model hallucinations through prompt engineering and edge-case analysis.
I performed high-quality data annotation and response evaluation to improve Large Language Model (LLM) outputs. I applied post-training evaluation techniques to ensure consistency and factual correctness in model responses. I designed and refined prompt-response pairs and evaluation guidelines for diverse scenarios. • Conducted supervised fine-tuning (SFT) support and human feedback evaluation tasks. • Focused on improving LLM reasoning, accuracy, and instruction alignment. • Used the MultiMango platform for data labeling and evaluation. • Helped reduce model hallucinations through prompt engineering and edge-case analysis.
2026 - 2026