Hepatocellular carcinoma (HCC) is one of the most common malignant tumors worldwide. Increasing evidence suggests that the dysregulation of RNA-binding proteins (RBPs) is involved in the development of various cancers. However, there is a paucity of studies investigating the roles of RBPs in HCC. Data on HCC samples were downloaded from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases (available at: www.ncbi.nlm.nih.gov/geo), and data regarding human RBPs were integrated from SONAR, XRNAX, and CARIC results. We identified modules associated with prognosis using weighted gene co-expression network analysis (WGCNA) and performed functional enrichment analysis. Univariate and least absolute shrinkage and selection operator (LASSO) regression analyses were used to identify prognostic RBPs and establish a prediction model. According to the median risk score, we separated patients into high- and low-risk groups and investigated the differences in immune cell infiltration, somatic mutations, and gene set enrichment. Univariate and multivariate regression analyses were used to identify prognostic factors for HCC. A nomogram was constructed, and its performance was evaluated with calibration curves. Sixteen RBPs (MEX3A, TTK, MRPL53, IQGAP3, PFN2, IMPDH1, TCOF1, DYNC1LI1, EIF2B4, NOL10, GNL2, EIF1B, PSMD1, AHSA1, SEC61A1, and YBX1) were identified as prognostic genes, and a prognostic model was established. Survival analysis indicated that the model had good predictive performance and that a high-risk score was significantly related to a poor prognosis. Additionally, there were significant differences in immune cell infiltration, somatic mutations, and gene set enrichment between the high- and low-risk groups. Univariate and multivariate regression analyses indicated that the RBP-based signature was an independent prognostic factor for HCC. The nomogram based on 16 RBPs performed well in predicting the overall survival of HCC patients. The RBP-based signature is an independent prognostic factor for HCC, and this study could provide an innovative method for analyzing prognostic biomarkers and therapeutic targets for HCC.