AI Workflow Automation Specialist (AI Content Evaluator / Prompt Engineer / RLHF Evaluator)
As an AI Workflow Automation Specialist, I designed and evaluated LLM prompt workflows using structured rubrics for output assessment. I authored prompt-golden answer pairs and developed response iterations to benchmark model behavior. My work focused on reducing prompt failure rates and developing robust evaluation documentation. • Designed and tested LLM prompts with multi-constraint criteria • Authored and iterated golden-answer pairs for standardized LLM benchmarking • Conducted rubric-based RLHF feedback and evaluation on Claude, GPT-4, and open-source models • Configured Make.com and n8n workflows integrating Claude API and OpenRouter