Systems Performance Engineer

Responsibilities

• Build and improve systems software tools for profiling and analyzing LLM training and inference workloads
• Design and evaluate KV-cache and state-management strategies for LLM serving
• Develop data placement, migration, and prefetching algorithms across HBM, CXL, and NVMe memory tiers
• Characterize and optimize LLM execution engines, including attention behavior and batching strategies
• Analyze rack-scale and cluster-scale inference deployments focusing on throughput, latency, and token economics
• Instrument and analyze performance across GPUs, CPUs, memory subsystems, and interconnects to identify bottlenecks
• Collaborate with architecture and research teams to influence next-generation AI platforms and memory designs

Requirements

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field
• Strong foundation in operating systems, memory systems, parallel computing, or distributed systems
• Proficiency in systems programming using C/C++ and Python
• Experience working in Linux environments, including debugging and profiling
• Solid understanding of modern server architectures, including GPUs, CPUs, and cache hierarchies

Preferred Qualifications

• Experience with LLM training and inference systems and execution runtimes
• Hands-on experience with KV cache management or long-context execution
• Familiarity with multi-tier memory systems such as HBM, CXL-attached memory, and NVMe
• Experience profiling AI inference pipelines and latency-sensitive workloads
• Exposure to memory or system simulators like gem5 or Ramulator

About the Company

Micron Technology is a world leader in innovating memory and storage solutions that accelerate the transformation of information into intelligence, inspiring the world to learn, communicate and advance faster than ever.