Senior staff AI/HPC Infrastructure Engineer

The AI/HPC Infrastructure Engineer will modify and operate advanced GPU computing platforms for AI training, inference, and memory-system research. The engineer will work at the intersection of AI infrastructure, LLM serving, memory architecture, storage systems, and AI workload characterization. The role supports development of next-generation HBF,  SSD, and memory-centric AI systems through hardware/software co-design and real-world AI workload analysis.

Essential Duties and Responsibilities:

Build and Modify AI/HPC Research Infrastructure

• Build AI testbeds supporting 8-100+ GPU environments
• Manage server, networking, storage, and software infrastructure
• Support cloud-scale and edge-AI deployment models
• Develop benchmarking and validation environments for emerging AI workloads

Deploy and Optimize LLM Serving Platforms

• Install and optimize:
  • vLLM
  • NVIDIA Dynamo
  • TensorRT-LLM
  • Triton Inference Server
  • SGLang
• Support distributed inference and agentic AI workloads
• Optimize latency, throughput, and GPU utilization
• Evaluate inference cost and scalability across different architectures

AI Workload Characterization

• Capture workload traces from training and inference platforms
• Analyze:
  • Memory bandwidth
  • KV-cache growth
  • Storage access patterns
  • Network traffic
• Develop forecasting models for future memory such as HBF and storage requirements
• Generate insights that guide next-generation memory product development

AI Memory and Storage Architecture Evaluation

• Evaluate system bottlenecks across:
  • SSD
  • Networking
  • GPU interconnects
• Prototype new memory-system architectures
• Study disaggregated memory and storage approaches
• Validate AI infrastructure benefits of future SANDISK technologies

Digital Twin and Simulation

• Build simulation environments for AI systems
• Develop digital-twin platforms based on real workload traces
• Model future AI infrastructure configurations
• Evaluate performance of future HBM, SSD, and memory products before silicon availability

Research and Ecosystem Collaboration

• Collaborate with:
  • Universities
  • Startup companies
  • National laboratories
  • Cloud service providers
  • System OEMs
• Jointly evaluate emerging AI infrastructure architectures
• Publish technical papers and contribute to industry standards

Required: 

AI Infrastructure

• Linux
• Kubernetes
• Docker
• Slurm
• Python
• GPU cluster administration
• Distributed systems engineering

AI Serving

• vLLM
• NVIDIA Dynamo
• TensorRT-LLM
• Triton
• SGLang
• Agentic AI frameworks
• RAG systems

Networking and Scale-Out Systems

• InfiniBand
• RoCE
• RDMA
• NCCL
• Multi-node inference
• Distributed AI clusters

(These are not explicitly listed in all openings but are highly relevant to the AI/HPC infrastructure responsibilities described in the positions.)

AI System Architecture

• AI accelerator architecture
• Memory hierarchy optimization
• SSD architecture
• Storage-memory co-design
• AI performance modeling
• Hardware/software co-design

What SANDISK Would Likely Expect

The AI/HPC engineer is expected to do three things simultaneously:

1. Operate advanced AI infrastructure.
2. Understand AI workloads deeply enough to identify memory and storage bottlenecks.
3. Translate those findings into future SSD, HBF, and AI-memory product requirements.

For the AI lab, the ideal candidate would be someone who has hands-on experience with vLLM, Dynamo, Ray, RDMA, KV-cache optimization, GPU clusters, and AI performance characterization, because that person can both run the infrastructure and provide direct feedback for future memory-system innovation.