LLM Inference Systems Performance Engineer

3M HEALTHCARE; Austin (TX); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Medical, dental, and vision coverage

Income protection benefits

Paid family leave

Paid time off and holidays

Job summary

Micron Technology is seeking an engineer to work on AI training and inference systems, focusing on LLM execution engines, memory hierarchies, and performance optimization across data-center platforms.

The role involves end‑to‑end profiling, benchmarking, and collaboration with senior engineers and researchers. You will develop tools and methods to improve throughput, latency, and resource utilization for large-scale AI workloads.

Qualifications

• Bachelor’s or Master’s degree in CS/EE or equivalent experience.
• Proficiency in C/C++ and Python.
• Experience in Linux environments, debugging, profiling, and automation.
• Solid understanding of memory systems, NUMA, GPUs, and server architectures.
• Strong written and verbal communication skills.

Responsibilities

• Profile and optimize LLM training and inference workloads.
• Design and evaluate KV-cache and state-management strategies for LLM serving.
• Build benchmarking, simulation, and emulation frameworks for AI workloads across memory tiers.
• Develop data placement, migration, and prefetching algorithms for heterogeneous memory pools.
• Characterize LLM execution engines and analyze throughput and latency across deployments.
• Collaborate with engineering, architecture, and research teams to influence future AI systems.

Skills

C/C++ programming

Python

Linux

Memory systems

Performance profiling

System optimization

Communication

Education

Bachelor’s or Master’s in CS/EE

Tools

gem5

Ramulator

Perf tooling

Job description

Micron Technology is seeking an engineer to work on AI training and inference systems, focusing on LLM execution engines, memory hierarchies, and performance optimization across data-center platforms.

The role involves end‑to‑end profiling, benchmarking, and collaboration with senior engineers and researchers. You will develop tools and methods to improve throughput, latency, and resource utilization for large-scale AI workloads.