Senior AI Systems Engineer — High-Performance Inference

DDN; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

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.

Qualifications

• Experience building or optimizing production AI systems, not only experimentation.
• Understand how inference performance is shaped by compute, memory, storage, and serving architecture.
• Hands‑on work close to the systems layer, optimizing workloads across GPU/CPU and reducing bottlenecks.
• Real ownership in areas like model serving, retrieval, caching, storage, or distributed performance.
• Ability to move between architecture decisions and hands‑on implementation in scalable environments.
• Background in AI infrastructure, high‑performance systems, or adjacent distributed systems.

Responsibilities

• Build and optimize LLM serving and inference systems for production environments.
• Improve performance across GPU and CPU pathways.
• Work on KV cache, memory, storage, and throughput bottlenecks.
• Design and scale systems that support RAG and retrieval‑heavy AI workloads.
• Contribute to infrastructure where storage architecture and systems efficiency affect AI performance.
• Solve engineering problems at the intersection of AI, high‑performance systems, and distributed infrastructure.

Skills

Production AI systems experience

Inference performance optimization

Systems-level engineering

Ownership in model serving/retrieval/c

Architecture-to-implementation fluency

AI infrastructure or HPC background

Education

PhD preferred

Tools

GPU/CPU resource tuning

Distributed storage systems

Job description

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.