DDN seeks an engineer to build and optimize production AI systems, focusing on fast inference across GPU and CPU paths. You’ll tackle bottlenecks in memory, storage, and KV caching while designing scalable infrastructure for RAG and retrieval‑heavy workloads.
You will own critical areas from architecture decisions to hands‑on implementation, operating in technically demanding environments where efficiency and scale determine success. PhD preferred but practical impact matters most.
#J-18808-Ljbffr