In this article, we examine the relationship between self-reported opioid use and employment outcomes among Social Security Disability Insurance (SSDI) applicants who applied to SSDI in 2009. We use a machine learning method to identify opioids recorded in text fields on SSDI applications. Studying outcomes for 4 years after the U.S. Social Security Administration (SSA) determined the application outcome, we find a negative and statistically significant association between self-reported opioid use at application and post-determination employment-related outcomes. Notably, opioid use at the time of application was associated with a 3% point decline in the likelihood of employment in the first 4 years after determination and represents a 7.5% decline relative to the mean employment rate for the period. Results from a reduced-form model estimating the relationship between local opioid prescribing patterns and employment outcomes suggest that a 10% increase in the local opioid prescribing rate is associated with employment that is, at most, 0.3% points lower, which is similar to the documented association among the broader U.S. population. However, the potential implications for SSDI applicants are particularly notable because opioid use is about 50% higher among SSDI applicants.