Principal SoC Performance Architect for AI & HPC Platforms

Arm Limited; Austin (TX); Hybrid; USD 250,000 - 338,000; Full time

Job summary

Arm is seeking experienced performance architects to push the boundaries of modern server systems. You will work at the intersection of architecture, workload characterization, and silicon-level analysis to understand and improve real-world system behavior.

Join a team that designs future platforms by combining deep architectural expertise with practical investigations on silicon and large-scale workloads. This role offers leadership in benchmarking, cross-team collaboration, and end-to-end

Qualifications

• Master’s or PhD in Computer Engineering, CS, or related field.
• 10+ years in system or hardware architecture.
• Experience with CPU/accelerator architectures, caches, PCIe/Networking/Storage.
• Strong background in high-performance IO or HPC/cloud systems.
• Benchmarking methodologies and custom microbenchmarks.
• Profiling tools, performance analysis, and simulators.
• Proficient in SystemC, TLM, C++, and Python.
• Ability to navigate large, complex codebases.

Responsibilities

• Evaluate and analyze real-world workloads on production silicon, with a strong focus on AI at scale and HPC.
• Partner with multi-functional teams to define performance metrics, representative use cases, and benchmarking strategies.
• Design and implement targeted microbenchmarks to isolate and study specific architectural behaviors.
• Identify performance bottlenecks through detailed analysis and recommend actionable optimizations.
• Translate insights from workload and silicon studies into architectural improvements for performance and scalability.
• Collaborate closely with hardware and software teams to influence system-level design decisions.
• Serve as a performance expert, providing technical leadership and guidance across teams.
• Drive end-to-end understanding from architecture workload silicon validation to best-in-class system performance.

Skills

CPU architectures

Performance optimization

Benchmarking

SystemC/TLM

C++

Python

Large codebases

Education

MS/PhD in CS/CE

Tools

SystemC

TLM

C++

Python

Job description

Arm is seeking experienced performance architects to push the boundaries of modern server systems. You will work at the intersection of architecture, workload characterization, and silicon-level analysis to understand and improve real-world system behavior.

Join a team that designs future platforms by combining deep architectural expertise with practical investigations on silicon and large-scale workloads. This role offers leadership in benchmarking, cross-team collaboration, and end-to-end