Responsibilities:Design a unified AI Infra and Serving architecture platform for composite AI workloads such as LLM Training and Inference, RLHF, Agent, and Multimodal processing. This platform will integrate inference, orchestration, and state management, defining the technical evolution path for Serverless AI + Agentic ServingDesign a heterogeneous execution framework across CPU/GPU/NPU for agent me click apply for full job ..... full job details .....