Memory Systems Performance & Workload Architect

Responsibilities

• Lead Micron’s workload-driven memory architecture and performance strategy across mobile and server-class platforms.
• Define industry-leading benchmarking frameworks for mobile (Geekbench, MLPerf Mobile) and server (SPEC, STREAM, MLPerf) environments.
• Characterize memory bandwidth, latency, QoS, access patterns, and NUMA behavior to guide product decisions.
• Perform deep-dive root cause analysis using PMU counters, perf, eBPF, and ftrace to identify bottlenecks in memory controllers and DRAM timing.
• Drive system-level tradeoff analysis involving performance, power, cost, and scalability.
• Establish advanced frameworks for performance modeling, analytical simulation, and trace-driven workload replay.
• Partner with ecosystem teams to optimize AI frameworks, databases, and virtualization platforms for memory efficiency.

Requirements

• 15–24+ years of experience in memory systems, performance engineering, or system architecture.
• Proven expertise in workload analysis and characterization for both server and mobile platforms.
• Strong programming proficiency in Python and C/C++.
• Deep experience with benchmarking suites such as SPEC, MLPerf, and STREAM.
• Extensive knowledge of Linux performance tools including perf, eBPF, and PMU-based profiling.
• Advanced degree (Master's or PhD) with relevant years of experience, or a Bachelor's degree with 15+ years of experience.

Preferred Qualifications

• Experience optimizing AI/ML workloads, including LLMs and training clusters.
• Expertise in cloud-native systems and databases such as RocksDB, MySQL, or Redis.
• Proficiency in performance modeling, simulation, and trace-driven workload replay frameworks.
• Familiarity with ARM and x86 system architectures and associated performance tooling.

About the Company

Micron Technology is a world leader in innovating memory and storage solutions that accelerate the transformation of information into intelligence. We deliver a rich portfolio of high-performance DRAM, NAND, and NOR memory and storage products that fuel the data economy, enabling advances in artificial intelligence, 5G, and the intelligent edge.