The Amharic language is widely spoken in Ethiopia by over 31.8 million people as their mother tongue, and an additional 25 million as second-language speakers. It is also used to document a significant portion of Ethiopia’s historical and literary records. However, recognizing handwritten and machine-printed characters in Amharic has been a challenging issue. Several OCR technologies have been proposed to address this issue, but it remains unresolved. This study proposes a convolutional neural network (CNN) model for Amharic character recognition. The model was developed using 104,177 Amharic character images and subjected to data preprocessing activities such as binarization and noise removal. The dataset was partitioned into training, validation, and test sets, with each partition containing 80%, 10%, and 10% of the data, respectively. The proposed model's hyperparameters were optimized using three algorithms: random search, Bayesian optimization, and hyperband optimization. Results showed that the random search algorithm produced the best performance, achieving 96.02% accuracy when tested with unseen data. The study concludes that increasing the dataset size and tuning the hyperparameters under different scopes could further improve the model's performance. In general, this study provides a promising approach to Amharic character recognition using deep learning techniques.