Nov 2025 – Jan 2026 · 2 mos · United States · Remote

• LLM Trainer with hands-on experience in training and evaluating large language models for generative AI systems. Worked on system prompt design, structured user–assistant turn creation, turn-level metadata annotation, and response quality evaluation. Actively involved in human rewrites to improve accuracy, coherence, and instruction adherence. Experienced in analyzing model performance reports and applying evaluation insights to enhance output quality. Strong understanding of prompt engineering, NLP fundamentals, and human-in-the-loop AI workflows.