Datacenter Server & AI Product Architect

AMD; United States; Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Benefits at a glance

Job summary

AMD is seeking a Server and AI Product Architect for its Datacenter System Architecture & Engineering team to craft end-to-end EPYC and Instinct GPU product architectures. You will engage customers, architects, and internal stakeholders to map requirements across Si, HW/SW, and platform usage for optimal performance and scale.

The role demands deep expertise in memory, I/O, power, thermal, and boot processes, with a track record of delivering innovative server and GPU solutions and

Qualifications

• Strong analytical and problem-solving abilities with attention to detail.
• Ability to drive tasks independently and meet deadlines.
• Experience with server/enterprise AI/HPC product architecture.

Responsibilities

• Define architecture for EPYC and Instinct GPU products spanning Si, HW/SW, and platforms.
• Collaborate with customers, processor/IP/SOC teams, and software groups to specify requirements.
• Lead next-gen datacenter compute designs to improve performance.
• Shape future products through architecture and technology execution.
• Demonstrate deep knowledge of memory, I/O, power, thermal, and boot processes.
• Engage with top tech companies to engineer differentiated solutions.

Skills

Server architecture

GPU architecture

Power delivery

Memory I/O

Thermal management

Cross-functional teamwork

Education

Bachelors or Masters in electrical or computer engineering

Job description

AMD is seeking a Server and AI Product Architect for its Datacenter System Architecture & Engineering team to craft end-to-end EPYC and Instinct GPU product architectures. You will engage customers, architects, and internal stakeholders to map requirements across Si, HW/SW, and platform usage for optimal performance and scale.

The role demands deep expertise in memory, I/O, power, thermal, and boot processes, with a track record of delivering innovative server and GPU solutions and