I’m a detail-oriented AI evaluator and data-driven engineer with 4+ years of experience in data analysis, automation, and quality-focused investigation. I evaluate multimodal LLM outputs for text-to-image generation and image editing using rubric-based criteria like instruction following, visual quality, consistency, and human preference alignment, and I provide clear feedback to identify failure patterns. I also build automated workflows and dashboards using Python, SQL, and BI tools to validate results, track quality trends, and improve efficiency. Reliable, consistent, and comfortable with ambiguity, I work independently and stay focused on complex tasks.