During the summer of 2015, a number of large wildfires burned across northern California in areas of localized topographic relief. Persistent valley smoke hindered fire‐fighting efforts, delayed helicopter operations, and exposed communities to extreme concentrations of particulate matter. It was hypothesized that smoke from the wildfires reduced the amount of incoming solar radiation reaching the ground, which resulted in near‐surface cooling, while smoke aerosols resulted in warming aloft. As a result of increased inversion‐like conditions, smoke from wildfires was trapped within mountain valleys adjacent to active wildfires. In this study, wildfire smoke‐induced inversion episodes across northern California were examined using a modeling framework that couples an atmospheric, chemical, and fire spread model. Modeling results examined in this study indicate that wildfire smoke reduced incoming solar radiation during the afternoon, which lead to local surface cooling by up to 3°C, which agrees with cooling observed at nearby surface stations. Direct heating from the fire itself did not significantly enhance atmospheric stability. However, mid‐level warming (+0.5°C) and pronounced surface cooling was observed in the smoke layer, indicating that smoke aerosols significantly enhanced atmospheric stability. A positive feedback associated with the presence of smoke was observed, where local smoke‐enhanced inversions inhibited the growth of the planetary boundary layer, and reduced surface winds, which resulted in smoke accumulation that further reduced near‐surface temperatures. This work suggests that the inclusion of fire‐smoke‐atmosphere feedbacks in a coupled modeling framework such as WRF‐SFIRE‐CHEM can forecast the dispersion of wildfire smoke and its radiative feedbacks, and potentially provide decision‐support for wildfire operations.