Senior SoC RAS Architect for Data Center Reliability

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

Benefits offered by this job

Accommodations

Hybrid working

PTO & benefits

Sabbaticals & parental leave

Job summary

Arm Limited is seeking an experienced SoC Reliability, Availability and Serviceability (RAS) Architect to drive the RAS strategy for next‑gen SoCs. You will collaborate with design, verification, manufacturing and product engineering to deliver robust RAS across diverse workloads and environments.

You will define architectural specs, roadmap RAS initiatives, and partner with hardware and software teams to realize efficient architectures for data center applications and lifecycle stages.

Qualifications

• Master’s degree in Computer Engineering, Computer Science, Electrical Engineering, or a related discipline.
• 10+ years of experience in SoC development with a focus on RAS architecture.
• Deep understanding of data center availability and reliability expectations.
• Expertise in fault detection, error handling, and resiliency techniques for large-scale compute platforms.

Responsibilities

• Define reliability, availability, and serviceability (RAS) requirements for next-generation SoCs.
• Architect scalable RAS solutions balancing power, performance, and area (PPA).
• Develop reliability-aware design techniques such as ECC, parity, error logging, detection, and mitigation.
• Lead RAS efforts across the product lifecycle with front-end design, physical implementation, and verification teams.
• Align with cross-functional teams to meet data center-class reliability standards.

Skills

RAS architecture

Data center reliability

Fault detection

Error handling

Education

Master’s degree in Computer Engineering, Computer Science, Electrical Engineering, or a related discipline

Job description

Arm Limited is seeking an experienced SoC Reliability, Availability and Serviceability (RAS) Architect to drive the RAS strategy for next‑gen SoCs. You will collaborate with design, verification, manufacturing and product engineering to deliver robust RAS across diverse workloads and environments.

You will define architectural specs, roadmap RAS initiatives, and partner with hardware and software teams to realize efficient architectures for data center applications and lifecycle stages.