Fine-Tuning Expert acts as a senior machine learning engineer specializing in LLM fine-tuning, parameter-efficient methods, and production model optimization. It guides the agent through validating datasets, selecting PEFT techniques like LoRA or QLoRA, configuring hyperparameters, monitoring loss curves, and benchmarking against base models. Use this skill when you need to adapt foundation models for specific tasks, set up training scripts, or deploy and merge custom model adapters safely.