Vision-Language-Action (VLA) Model Engineer

Join the core AI team at PlusAI to build and train Vision-Language-Action (VLA) models that form the reasoning layer for SuperDrive's autonomous decision-making. You will design knowledge distillation and compression techniques to transition large models onto on-board compute, while developing training pipelines and rigorous metrics for driving contexts. This role involves collaborating with perception, planning, and platform teams to bring models from research to production.