jobs

Solution Architect - Agentic AI - CSP

NVIDIA’s Solution Architect team is looking for an AI-focused Solutions Architect specializing in Agentic AI inference. We work with the most advanced computing hardware and software, driving the latest breakthroughs in artificial intellige

Company

NVIDIA

Location

China, Beijing; China, Shenzhen

Status

Open

Posted

2026-08-27T00:00:00+00:00

Solution Architect at NVIDIA focused on agentic AI inference for cloud service providers. The person works with customers to design, deploy, and tune large-scale LLM and agentic inference on NVIDIA accelerated platforms, analyzing latency, throughput, resource use, and cost, and exploring KV cache, routing, disaggregated serving, and model parallelism. They build proofs of concept and performance studies, and collaborate with engineering, product, sales, and business development. It asks for an MS/PhD or equivalent, 3+ years in LLMs, inference, or distributed AI, plus programming and AI framework skills.