Abstract Scale invariant neural dynamics are a relatively new but effective means of measuring changes in brain states as a result of varied cognitive load and task difficulty. This study is the first to test whether scale invariance (as measured by the Hurst exponent, H ) can be used with functional near-infrared spectroscopy (fNIRS) to quantify cognitive load. We analyzed H extracted from the fNIRS time series while participants completed an N-back working memory task. Consistent with what has been demonstrated in fMRI, the current results showed that scale-invariance analysis significantly differentiated between task and rest periods as calculated from both oxy- (HbO) and deoxy-hemoglobin (HbR) concentration changes. Results from both channel-averaged H and a multivariate partial least squares approach (Task PLS) demonstrated higher H during the 1-back task than the 2-back task. These results were stronger for H derived from HbR than from HbO. As fNIRS is relatively portable and robust to motion-related artifacts, these preliminary results shed light on the promising future of measuring cognitive load in real life settings. Author Summary Scale invariance reflects a pattern of self-similarity (or fractalness) across a time series of brain data. In human neuroscience studies using EEG and fMRI, higher scale invariance has been associated with individuals being in a state of minimal cognitive effort or while performing a relatively easy task compared to doing something more challenging. Functional near-infrared spectroscopy (fNIRS) is a flexible neuroimaging technique that can be used in naturalistic settings and measures the same underlying biological signal as fMRI. We expected that, if scale invariant brain states are indeed robust indicators of cognitive load or task difficulty, we should be able to replicate previous findings in fNIRS. Consistent with this hypothesis, we find that more scale invariant brain states are indeed associated with less cognitively demanding and more restful brain states in fNIRS data. This finding opens up a wide array of potential applications for monitoring cognitive load and fatigue in real-life settings, such as during driving, learning in schools, or during interpersonal interactions.