AI Engineer & Software Developer
As an AI Engineer & Software Developer, I designed and implemented AI output evaluation pipelines across multiple LLMs. My work involved prompt engineering, systematic evaluation of model responses, and the provision of structured feedback for model improvement. I assessed model strengths and weaknesses to ensure training data quality alignment for AI models. • Developed and tested prompts to systematically rate AI output for factual accuracy, reasoning quality, and helpfulness. • Conducted A/B preference judgments and comparative analyses on LLM-generated responses. • Wrote clear, concise rationales for ranking and rewriting model outputs. • Built Python automation tools and API integrations to streamline labeling and assessment processes.