RAS Architect

Advanced Micro Devices, Inc • Austin, TX

9d

About The Position

AMD is seeking an experienced Reliability, Availability, and Serviceability (RAS) Architect to shape robust, resilient architectures for AMD products. The role defines and develops system-level RAS capabilities for complex computing systems and scale-out environments, collaborating with hardware engineers, system architects, software developers, vendors, and suppliers to identify failure modes and develop architectural solutions. The work covers RAS requirements, reliability analysis, fault detection and recovery, redundancy, diagnostics, system-level validation, and product development from architecture through early customer support.

The successful candidate brings strong analytical and problem-solving skills to complex system-level reliability challenges, communicates technical concepts clearly, collaborates across hardware and software disciplines, and evaluates technical trade-offs and potential points of failure to improve system resilience and availability.

Requirements

• Experience with system-level architecture design, reliability engineering, and fault-tolerance mechanisms for complex computing systems, data centers, or mission-critical applications.
• Experience developing and optimizing RAS architectures.
• Experience with fault-tolerant design principles and techniques, including redundancy, error correction codes (ECC), and error-recovery mechanisms.
• Experience with system-level simulation tools and methodologies, including fault injection, reliability block diagrams, and failure-rate analysis.
• Experience programming in C/C++ in Linux environments.
• Familiarity with Linux kernel internals and code review.
• Experience analyzing and resolving complex system-level technical issues.
• Demonstrated written and verbal communication skills and experience collaborating across engineering.
• BS, MS, or PhD in Electrical Engineering, Computer Science, or a related technical discipline preferred.

Nice To Haves

• Experience with system-level architecture design, reliability engineering, and fault-tolerance mechanisms for complex computing systems, data centers, or mission-critical applications.
• Experience developing and optimizing RAS architectures.
• Experience with fault-tolerant design principles and techniques, including redundancy, error correction codes (ECC), and error-recovery mechanisms.
• Experience with system-level simulation tools and methodologies, including fault injection, reliability block diagrams, and failure-rate analysis.
• Experience programming in C/C++ in Linux environments.
• Familiarity with Linux kernel internals and code review.
• Experience analyzing and resolving complex system-level technical issues.
• Demonstrated written and verbal communication skills and experience collaborating across engineering.
• BS, MS, or PhD in Electrical Engineering, Computer Science, or a related technical discipline preferred.

Responsibilities

• Design and develop server and embedded RAS architectures for AMD products, including solutions deployed in scale-out environments.
• Define and analyze reliability, availability, and serviceability requirements aligned with industry standards and customer expectations.
• Collaborate with hardware and software teams to identify potential points of failure, conduct failure mode and effects analysis (FMEA), and develop mitigation strategies.
• Develop fault detection, isolation, recovery, redundancy, and error-correction mechanisms to improve system resilience and availability.
• Define and implement advanced diagnostics and monitoring capabilities for proactive system health management and predictive maintenance.
• Collaborate with vendors and suppliers to assess and integrate RAS-related solutions into the overall system architecture.
• Conduct system-level simulations, analysis, and testing to validate and verify the effectiveness of RAS architectures and components.
• Evaluate advancements in RAS techniques, fault-tolerance mechanisms, and industry trends to inform future system designs.
• Contribute throughout product development, from product definition, architecture, and design through implementation, debugging, testing, and early customer support.

What This Job Offers

• Job Type: Full-time