The incorporation of industrial waste into concrete has emerged as an effective strategy for improving sustainability while reducing the environmental impacts associated with construction materials. Among these recycled materials, waste steel fibers have shown considerable potential as concrete reinforcement. To ensure their efficient utilization, however, reliable prediction of concrete performance is essential. Since direct measurement of compressive strength is often expensive, time-consuming, or impractical for existing structures, the development of accurate predictive models offers an attractive alternative. This research proposes an artificial intelligence-based approach for estimating the compressive strength of concrete reinforced with recycled steel fibers. An Artificial Neural Network (ANN) trained using the Levenberg–Marquardt algorithm was developed from an experimental database consisting of 45 different concrete mix designs. The input variables included steel fiber content, cement content, water content, water-to-cement ratio, and superplasticizer dosage, while the output parameter was the compressive strength measured at curing ages of 7, 28, and 60 days. For model development, the dataset was divided into training (75%), testing (15%), and validation (15%) subsets. Experimental observations demonstrated that incorporating recycled steel fibers enhanced the compressive strength of concrete, which can be attributed to the effective dispersion of fibers within the cementitious matrix and the use of an appropriate fiber dosage. The developed ANN successfully captured the relationship between mixture proportions and compressive strength, producing highly accurate predictions. The validation results yielded a correlation coefficient exceeding 99%, confirming the robustness, reliability, and predictive capability of the proposed neural network model for estimating the compressive strength of steel fiber-reinforced concrete.