A Machine Learning - Genetic Algorithm (MLGA) approach was developed to virtually discover optimum designs using training data generated from high-fidelity simulations. Machine learning (ML) presents a pathway to transform complex physical processes that occur in a combustion engine into compact informational processes. In the present work, a total of over 2000 sector-mesh computational fluid dynamics (CFD) simulations of a heavy-duty engine were performed. These were run concurrently on a supercomputer to reduce overall turnaround time. The engine being optimized was run on low-octane (RON70) gasoline fuel using a partially-premixed advanced combustion approach. A total of nine input parameters (or features) were varied, and the CFD simulation cases were generated by randomly sampling points from this nine-dimensional input space. These input parameters included fuel injection strategy, injector design and various in-cylinder flow and thermodynamic conditions at intake valve closure (IVC). The outputs (targets) of interest from these simulations included five performance and emission metrics. The over 2000 samples generated from CFD were then used to train a ML model that predicted these five targets based on the nine input features. A robust meta-learner approach was employed to build the ML model, where results from a collection of different ML algorithms were pooled together. Then, a stochastic global optimization genetic algorithm (GA) was used, with the ML model as the objective function, to optimize the input parameters based on a merit function constructed from the five targets. The results from the MLGA approach were found to be very close to a sequentially performed CFD-GA approach, where a CFD simulation served as the objective function. In addition, the overall turnaround time was an order of magnitude lower with the MLGA approach as the training data was generated from concurrent CFD simulations and employing the ML model as the objective function significantly accelerated the GA optimization. This study demonstrated the significant cost-savings potential of ML and high-performance computing with regard to design optimization.