Neuronal signaling is one of several approaches to network nanomachines in the human body. This paper formulates a noisy optimization problem for a neuronal signaling protocol based on Time Division Multiple Access (TDMA) and solves the problem with a noise-aware optimizer that leverages an evolutionary algorithm. The proposed optimizer is intended to minimize signaling latency by multiplexing and parallelizing signal transmissions in a given neuronal network, while maximizing signaling robustness (i.e., unlikeliness of signal interference). Since latency and robustness objectives conflict with each other, the proposed optimizer seeks the optimal trade-offs between them. It exploits a nonparametric (i.e.. distribution-free) statistical operator because it is not fully known what distribution(s) noise follows in each step/component in neuronal signaling. Simulation results show that the proposed optimizer efficiently obtains quality TDMA signaling schedules and operates a TDMA protocol by balancing conflicting objectives in noisy environments.