AI Memory Systems Engineer for Accelerators

Micron; San Jose (CA); On-site; USD 215,000 - 376,000; Full time

Benefits offered by this job

Medical, dental and vision plans

Paid time off and holidays

Income protection and paid familyLeave

Job summary

Micron Technology, a world leader in memory and storage solutions, seeks an engineer to advance DRAM systems for AI inference workloads in San Jose. You will explore memory architectures, OS components, and performance optimization across hardware and software, impacting AI accelerators and agentic workflows.

The role emphasizes research across hardware architecture, operating systems, and performance analysis, with collaboration across teams and a strong focus on memory systems and AI workloads.

Qualifications

• Bachelor's degree with 10+ years experience or higher degrees in CS/EE.
• Strong background in memory systems, OS, distributed or parallel computing.
• Proficiency in C/C++ and Python with hands-on systems programming.
• Experience in Linux environments, including shell scripting and debugging tools.
• Excellent communication and ability to work independently and in teams.

Responsibilities

• Characterize AI inference workloads and memory behavior.
• Build and evaluate tiered memory hierarchies for AI accelerators.
• Study KV cache lifecycles, MoE models, and data placement strategies.
• Compare and optimize explicit versus hardware-assisted data movement.
• Develop, test, debug, and detail system-level and OS components.
• Prototype and evaluate agentic AI systems using modern frameworks and orchestration patterns.

Skills

Memory systems

Operating systems

Distributed systems

Parallel computing

C/C++

Python

Systems programming

Linux

Shell scripting

Debugging tools

Team collaboration

Education

Bachelor's degree in CS/EE

Master's or PhD in CS/EE

Tools

CUDA

OpenCL

Job description

Micron Technology, a world leader in memory and storage solutions, seeks an engineer to advance DRAM systems for AI inference workloads in San Jose. You will explore memory architectures, OS components, and performance optimization across hardware and software, impacting AI accelerators and agentic workflows.

The role emphasizes research across hardware architecture, operating systems, and performance analysis, with collaboration across teams and a strong focus on memory systems and AI workloads.