The need for ensuring safety in AI subsystems within autonomous vehicles is obvious. How to achieve it is not. Standard safety engineering tools are designed for software that runs on general-purpose CPUs. But AI algorithms require more performance than CPUs provide, and the specialized processors employed to achieve this performance are very difficult to qualify for safety. How can we achieve the redundancy and very strict testing required to achieve safety, while also using specialized processors to achieve AI performance? How can ISO 26262 be applied to AI accelerators? How can standard automotive practices like coverage checking and MISRA coding guidelines be used? We believe that safe autonomous vehicle AI subsystems are achievable, but only with cross-industry collaboration. In this presentation, we’ll examine the challenges of implementing safe autonomous vehicle AI subsystems and explain the most promising approaches for overcoming these challenges, including leveraging standards bodies such as Khronos, MISRA and AUTOSAR.