Head of GPU Inference Performance

Baseten is seeking an Engineering Manager to lead part of the Inference Performance team. You will mentor a group of inference performance engineers and drive GPU-focused optimization across kernels, scheduling, and KV-cache management. The role blends technical depth with people leadership to accelerate model workloads on GPUs. You will hire, develop and support engineers, set direction, review designs, and partner across teams to deliver fast, efficient inference at scale for customers. #J-18808-Ljbffr US Health Partners, LLC