Time-sensitive optimization problems challenge the balance of optimality and the speed of relevance—including several commercial and military operations. In this research, we explore a use case on an optimized artillery aimpoint algorithm. This aimpoint algorithm is time sensitive because as targets move, the optimal aimpoint solution for engaging these targets changes. With any software, algorithms and their parameters add complexity and may be hard to interpret. In optimization, these parameters include gene pool size, selection, mutation rates, swarm spread and density, step increment, the type of convergence algorithm, and so on. To prevent susceptibility of human misconception about optimization parameters and algorithms, meta-optimizations offer techniques to select ideal optimization parameters. Even the computer hardware, network architecture, and version numbers of software libraries influence the computational performance of generating solutions. Therefore, meta-optimizers should be trained using an operational profile and be adaptable to rapidly changing software by training them within the software release pipeline. This research explores the process and benefits of creating a tunable meta-optimizer. In the first stage, we start with a designed experiment around a resource intensive artificial intelligence or optimization application. This experiment collects responses (primarily processing time and local optimums) associated with a collection of input factors (the inputs of the objective function) and control factors (the optimization parameters). The goal of this data collection is to train a meta-model for the real optimization software. In the second stage, a meta-optimizer is trained. It takes the input factors joined with tuning parameter(s) to leverage our control factors. The meta-model is used to evaluate the tunable meta-optimizer in a reinforcement learning environment. The primary benefit for this tunable meta-optimizer design is to provide the operator control over the trade-off between optimality and time-sensitivity—a critical feature for managing scalability and deadlines.