Producers find a considerable amount of their operating expense (OPEX) comes from managing risks associated with corrosion and scale. Monitoring and chemical adjustment workflows are typically manual, and performed at low frequencies, leading to delays in event detection. As a result, the potential for negative events such as production shutdowns and well failures increase. This project's scope integrates chemistry domain experience with edge analytics, machine learning models, and intelligent equipment, to transform manual processes into an autonomous solution. The goal is to optimize operations, reduce well failures and workover costs, and maximize production. This solution is currently deployed in an oilfield, that has been historically challenged with a high number of electric submersible pump (ESP) failures due to corrosion and scale that resulted in significant production losses and unforeseen workover costs. The designed digital architecture supports autonomous management of scale and corrosion through remote monitoring and automated chemical injection. Real-time data is acquired from connected equipment, processed in an edge device running artificial intelligence, and autonomously sent to chemical pumps. Data from sensors, connected devices, and models are visualized in cloud applications, or integrated into existing client systems for end user analysis and full visibility of the entire process. The results show highly accurate models, precise chemical injection, and a reduction of well failures.