AI Infrastructure Systems Intern — Optimize LLM Workloads

Micron Technology, Inc; Austin (TX); On-site; USD 34,000 - 48,000; Full time

Benefits offered by this job

Medical, dental, and vision plans

Paid time off

Paid holidays

Job summary

Micron Technology, Inc. is seeking an AI Systems Software Engineering Intern to work with senior engineers on systems software for LLMs and Agentic AI applications.

You will profile, optimize, and evaluate AI workloads across GPU platforms and memory/storage systems. The role emphasizes profiling, workload characterization, and experimental evaluation to drive innovations in AI infrastructure and memory technologies.

Qualifications

• Currently pursuing a Master’s or Ph.D. in CS/CE/EE or related field.
• Experience with AI systems, ML systems, or systems software development through coursework or projects.
• Knowledge of LLMs, transformers, KV cache, batching, and memory performance considerations.

Responsibilities

• Develop and enhance systems software and profiling tools for LLM training and inference.
• Design memory and state-management techniques for AI serving environments.
• Characterize AI workloads across GPUs/CPUs/memory and optimize latency and throughput.
• Build benchmarking and automation for data placement and performance on heterogeneous memory systems.
• Collaborate to develop AI workloads and contribute to research publications and IP.

Skills

Python

C/C++

GPU profiling tools

LLM workloads

Linux environments

Education

Master’s or Ph.D. in Computer Science/Engineering

Tools

PyTorch

vLLM

TensorRT-LLM

CUDA

Job description

Micron Technology, Inc. is seeking an AI Systems Software Engineering Intern to work with senior engineers on systems software for LLMs and Agentic AI applications.

You will profile, optimize, and evaluate AI workloads across GPU platforms and memory/storage systems. The role emphasizes profiling, workload characterization, and experimental evaluation to drive innovations in AI infrastructure and memory technologies.