The problem of assembling effective expert teams based on project needs is central to expert networks such as LinkedIn. However, current team formation methods typically depend on keyword-matching techniques that fail to capture the nuanced semantics of natural language project descriptions. This results in inadequate modeling of required expertise and suboptimal team selection. Addressing this gap, we propose a contextual, prompt-driven framework for team formation that infers latent expertise from rich textual descriptions of project goals. Our approach fine-tunes a T5-Large sequence-to-sequence model to translate project prompts into expert team compositions by benefiting from enhanced expertise annotations. To facilitate this task, we curate, and publicly release, a dataset based on DBLP V14 collection, augmented with high-confidence expertise labels generated by large language models. Experimental results across multiple evaluation metrics show that our proposed model outperforms existing state-of-the-art baselines, underscoring the importance of contextualized representations in expert discovery and team assembly.