Senior staff AI/HPC Infrastructure Engineer

Sandisk; Milpitas (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Sandisk is seeking an AI/HPC Infrastructure Engineer to design and operate advanced GPU-based AI platforms for training, inference, and memory-system research. You will work at the intersection of AI infrastructure, LLM serving, memory architecture, storage systems, and workload characterization to drive next-generation memory products.

The role involves building scalable AI testbeds, deploying LLM serving stacks, and performing detailed workload analyses to optimize performance and cost across

Qualifications

• Linux, Kubernetes, Docker, Slurm, Python, GPU cluster administration.
• Distributed systems engineering and AI infrastructure expertise.
• Experience with vLLM, NVIDIA Dynamo, TensorRT-LLM, Triton, SGLang and RAG systems.

Responsibilities

• 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 AI workloads.
• Install and optimize vLLM, NVIDIA Dynamo, TensorRT-LLM, Triton, SGLang.
• Support distributed inference and agentic AI workloads.
• Optimize latency, throughput, and GPU utilization.
• Evaluate inference cost and scalability across architectures.
• Capture workload traces and analyze memory bandwidth, KV-cache growth, storage access patterns, network traffic.
• Develop forecasting models for future memory like HBF and storage requirements.
• Generate insights to guide memory product development.
• Prototype memory-system architectures; study disaggregated memory/storage; validate AI infrastructure benefits of Sandisk tech.
• Build simulation and digital-twin platforms; model future configurations.
• Collaborate with universities, startups, labs, cloud providers, OEMs; publish papers.

Skills

Linux

Kubernetes

Docker

Slurm

Python

GPU cluster administration

Distributed systems engineering

vLLM

NVIDIA Dynamo

TensorRT-LLM

Triton

SGLang

Agentic AI frameworks

RAG systems

InfiniBand

RoCE

RDMA

NCCL

Multi-node inference

Distributed AI clusters

AI accelerator architecture

Memory hierarchy optimization

SSD architecture

Storage-memory co-design

AI performance modeling

Hardware/software co-design

Tools

vLLM

NVIDIA Dynamo

TensorRT-LLM

Triton

SGLang

Job description

• Prototype new memory-system architectures
• Linux

Sandisk understands how people and businesses consume data and we relentlessly innovate to deliver solutions that enable today's needs and tomorrow's next big ideas. With a rich history of groundbreaking innovations in Flash and advanced memory technologies, our solutions have become the beating heart of the digital world we're living in and that we have the power to shape.

Sandisk meets people and businesses at the intersection of their aspirations and the moment, enabling them to keep moving and pushing possibility forward. We do this through the balance of our powerhouse manufacturing capabilities and our industry-leading portfolio of products that are recognized globally for innovation, performance and quality.

Sandisk has two facilities recognized by the World Economic Forum as part of the Global Lighthouse Network for advanced 4IR innovations. These facilities were also recognized as Sustainability Lighthouses for breakthroughs in efficient operations. With our global reach, we ensure the global supply chain has access to the Flash memory it needs to keep our world moving forward.

Description

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

• Operate advanced AI infrastructure.
• Understand AI workloads deeply enough to identify memory and storage bottlenecks.
• 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.

Additional Information

Sandisk is committed to providing equal opportunities to all applicants and employees and will not discriminate based on their race, color, ancestry, religion (including religious dress and grooming standards), sex (including pregnancy, childbirth or related medical conditions, breastfeeding or related medical conditions), gender (including a person's gender identity, gender expression, and gender-related appearance and behavior, whether or not stereotypically associated with the person's assigned sex at birth), age, national origin, sexual orientation, medical condition, marital status (including domestic partnership status), physical disability, mental disability, medical condition, genetic information, protected medical and family care leave, Civil Air Patrol status, military and veteran status, or other legally protected characteristics. We also prohibit harassment of any individual on any of the characteristics listed above. Our non-discrimination policy applies to all aspects of employment. We comply with the laws and regulations set forth in the Equal Employment Opportunity is the Law poster.

Sandisk thrives on the power and potential of diversity. As a global company, we believe the most effective way to embrace the diversity of our customers and communities is to mirror it from within. We believe the fusion of various perspectives results in the best outcomes for our employees, our company, our customers, and the world around us. We are committed to an inclusive environment where every individual can thrive through a sense of belonging, respect and contribution.

Sandisk is committed to offering opportunities to applicants with disabilities and ensuring all candidates can successfully navigate our careers website and our hiring process. Please contact us at [e-mail] to advise us of your accommodation request. In your email, please include a description of the specific accommodation you are requesting as well as the job title and requisition number of the position for which you are applying.