Fine-tuning means continuing the training of an already pre-trained AI model, such as an LLM, on a targeted dataset in order to specialize it for a task, a domain or a style without starting from scratch.
The most common form is supervised fine-tuning: you supply examples of questions and expected answers. Other methods adjust the model based on human preferences (RLHF, DPO). To reduce costs, techniques such as LoRA or QLoRA train only a small portion of the parameters, which makes the operation feasible on a few GPUs.
Fine-tuning is used to enforce an output format, a tone or domain vocabulary, or to get a small model to match a large one on a specific task, in order to lower inference costs.
It is not a good way to add knowledge that changes often: for that, RAG or a better prompt are usually simpler and easier to update. The choice depends on the problem, and is validated through evaluation.
Why it matters when hiring
Many candidates have run a fine-tuning job from a tutorial. Real depth shows in data preparation, setting up a before-and-after evaluation, and being able to say why fine-tuning was the right choice rather than RAG. It is the territory of a senior ML Engineer or AI Engineer; training foundation models, by contrast, calls for research profiles.