AI Trainer | Handshake (Remote)
Text
As an AI Trainer at Handshake, I was responsible for reviewing and evaluating AI-generated responses for accuracy and quality. I applied structured guidelines and complex scoring rubrics to assess outputs, identify errors, and improve model performance. My work involved providing actionable feedback to address bias, hallucinations, and edge cases in AI-generated text.
• Evaluated large language model outputs to ensure factual accuracy and coherence.
• Identified and flagged potential risks, including hallucinations and biases.
• Applied scoring rubrics to provide concise, structured feedback.
• Collaborated remotely and used internal/proprietary tools for annotation and evaluation.
As an AI Trainer at Handshake, I was responsible for reviewing and evaluating AI-generated responses for accuracy and quality. I applied structured guidelines and complex scoring rubrics to assess outputs, identify errors, and improve model performance. My work involved providing actionable feedback to address bias, hallucinations, and edge cases in AI-generated text. • Evaluated large language model outputs to ensure factual accuracy and coherence. • Identified and flagged potential risks, including hallucinations and biases. • Applied scoring rubrics to provide concise, structured feedback. • Collaborated remotely and used internal/proprietary tools for annotation and evaluation.
2023 - Present