Rhoda AI in Palo Alto is building the next generation of generalist intelligent robots. You will own end-to-end inference performance, diagnosing latency, throughput, and efficiency of large foundation models in production.
Collaborate with research engineers to translate model innovations into optimized, deployment-ready implementations using PyTorch, Triton, CUDA, and related tooling for multimodal models.
#J-18808-Ljbffr