AI Systems Engineer, Hardware Architecture

Job Title

AI Systems Engineer, Hardware Architecture

Role Summary

Principal-level hardware systems architect responsible for defining multi-year hardware architecture strategy for AI-accelerated computing across Meta Reality Labs devices (wearables, headsets, spatial computing platforms).

The role drives system-level decisions spanning custom silicon, memory subsystems, interconnects, and hardware-software co-design to meet on-device AI inference and training requirements.

Experience Level

Senior (principal-level). Guidance: 15+ years of experience in hardware systems architecture focused on AI/ML or high-performance compute systems.

Responsibilities

Lead architecture definition and cross-functional alignment for AI compute subsystems; evaluate trade-offs and provide technical leadership.

• Define and own multi-year architectural roadmaps for AI compute across hardware product lines.
• Lead system-level architecture exploration: memory hierarchy, interconnect topology, and power-performance-area tradeoffs.
• Drive alignment across silicon engineering, firmware, software, and product teams to convert AI workload needs into hardware specs.
• Develop and maintain architectural models, performance simulators, and analytical frameworks to evaluate design trade-offs.
• Identify and resolve architectural bottlenecks across the AI compute stack, from operators to microarchitecture.
• Set technical direction for platform decisions, including custom silicon vs third-party IP strategies.
• Partner with ML researchers and compiler teams to co-design hardware-software interfaces for efficient on-device models.
• Represent architecture in executive technical reviews and author architecture decision records and specifications.
• Mentor engineers across hardware architecture and systems engineering disciplines.

Requirements

Must-have technical experience and demonstrable track record; preferred items listed separately.

• Must-have: 15+ years in hardware systems architecture focused on AI, ML, or high-performance compute.
• Must-have: Experience defining SoC or system-level architecture for AI inference or training, including memory subsystem design, compute hierarchy, and interconnect topology.
• Must-have: Experience with hardware-software co-design for on-device AI, familiar with ML compiler concepts, operator fusion, and quantization impacts.
• Must-have: Experience developing system performance models and using simulation/analytical frameworks to evaluate architectural trade-offs.
• Must-have: Proven track record of driving multi-year hardware architecture roadmaps and influencing silicon strategy across large organizations.
• Nice-to-have: Familiarity with custom silicon development flows (architecture-to-RTL, physical design, post-silicon validation).
• Nice-to-have: Experience architecting AI systems for power- and area-constrained wearable or mobile devices (VR/AR/spatial computing).
• Nice-to-have: Experience evaluating and integrating emerging memory technologies (HBM, LPDDR5X, in-memory compute).
• Nice-to-have: Experience collaborating with ML research teams to map novel model architectures to hardware-efficient deployments.

Education Requirements

Not specified.

About the Company

Company: Meta Platforms

Headquarters: Menlo Park, California, United States

American technology company that develops social networking products (Facebook, Instagram, WhatsApp) and invests in virtual/augmented reality hardware and software through Reality Labs, focusing on connectivity, advertising, and immersive computing experiences.