Multimodal AI Prompt Engineer & Model Evaluator
VideoQuestion Answering
As a Multimodal AI Prompt Engineer & Model Evaluator, I design complex, context-rich prompts using video content to test advanced large language models (LLMs). My workflow includes extracting actionable insights from audio, visual, and textual cues, and structuring these into high-quality question-and-answer datasets. I refine these prompts through iterative cycles, ensuring strict standards in factual accuracy and logical coherence.
• Developed test prompts to evaluate model comprehension and reasoning
• Extracted relationships and actions from multimodal scenes
• Incorporated reviewer feedback to improve prompt clarity and difficulty
• Synthesized complex information into structured evaluation content
As a Multimodal AI Prompt Engineer & Model Evaluator, I design complex, context-rich prompts using video content to test advanced large language models (LLMs). My workflow includes extracting actionable insights from audio, visual, and textual cues, and structuring these into high-quality question-and-answer datasets. I refine these prompts through iterative cycles, ensuring strict standards in factual accuracy and logical coherence. • Developed test prompts to evaluate model comprehension and reasoning • Extracted relationships and actions from multimodal scenes • Incorporated reviewer feedback to improve prompt clarity and difficulty • Synthesized complex information into structured evaluation content
2019 - Present