LLM Post Training Intern - Ethara.AI
Text
As an LLM Post-Training Intern at Ethara AI, I evaluated and improved AI model outputs through structured annotation tasks. My work focused on providing quality assessments and targeted feedback to ensure the outputs met instruction-following and factual accuracy criteria. I applied company quality guidelines to refine AI-generated content and supported the continuous improvement of language models.
• Conducted systematic evaluation and post-training review of LLM model responses.
• Labeled AI outputs for accuracy, consistency, and adherence to guidelines.
• Provided detailed reasoning and objective feedback on model outputs.
• Collaborated within an AI team to enhance model alignment and reduce biased or irrelevant outputs.
As an LLM Post-Training Intern at Ethara AI, I evaluated and improved AI model outputs through structured annotation tasks. My work focused on providing quality assessments and targeted feedback to ensure the outputs met instruction-following and factual accuracy criteria. I applied company quality guidelines to refine AI-generated content and supported the continuous improvement of language models. • Conducted systematic evaluation and post-training review of LLM model responses. • Labeled AI outputs for accuracy, consistency, and adherence to guidelines. • Provided detailed reasoning and objective feedback on model outputs. • Collaborated within an AI team to enhance model alignment and reduce biased or irrelevant outputs.
2024 - Present