This work describes an early phase study designed to evaluate the safety and efficacy of the combination of modulated dose chemotherapy and immunotherapy for non-small cell lung cancer patients in each of two cohorts. The trial uses a model-based adaptive design to navigate treatment combinations in order to make treatment recommendations. The aim of the trial is to find the optimal dose combination, defined as the combination with the highest response rate among combinations with an acceptable level of toxicity. The primary outcomes which guide accrual decisions include treatment related dose-limiting toxicities and pathologic response, assessed between 12 and 28 weeks from start of treatment. Radiographic response, assessed at 6 weeks from start of treatment, is used as a surrogate for pathologic response until information on pathologic response becomes available. The trial design described is a practical approach to identifying the optimal treatment combination, where safety and efficacy are both of interest, while incorporating early and late efficacy information.