AI Hardware Architect — On-Device ML & Imaging for XR

Meta; United States; Remote; USD 210,000 - 320,000; Full time

Job summary

Meta is seeking a senior hardware systems architect to define architecture strategy for on-device AI in wearables, AR/VR devices. You will shape compute and memory hierarchies, camera/IP pipelines, and SoC interfaces, guiding cross-functional teams toward energy-efficient, scalable solutions.

You will lead multi-year roadmaps, evaluate trade-offs, and build models to forecast performance under real AI workloads.

Qualifications

• 12+ years hardware systems architecture experience in AI, imaging, or HPC.
• Deep knowledge of camera pipelines and end-to-end imaging system design.
• Experience defining AI workloads on SoC or system-level architectures.
• Familiarity with real-time computer vision, depth sensing, or VIO.
• Knowledge of hardware/software co-design for on-device AI and imaging workflows.
• Ability to build performance models and evaluate trade-offs with simulations.

Responsibilities

• Develop multi-generation architecture plans for on-device AI inference and training.
• Evaluate compute, memory, interconnect, and power trade-offs for target workloads.
• Architect camera pipelines, sensor interfaces, ISP, and multi-camera synchronization.
• Set requirements and targets for AI accelerators, image processors, and SoCs.
• Build performance models and simulations to compare designs under real workloads.
• Collaborate with silicon, firmware, camera, and ML teams to boost end-to-end performance and energy efficiency.
• Provide technical direction and communicate architecture decisions to leadership.
• Assess external technologies and suppliers for long-term roadmap planning.

Skills

AI hardware

Imaging systems

SoC design

Memory interconnect

Performance modeling

Hardware-software co-design

Tools

ML compiler

Simulation tools

Job description

Meta is seeking a senior hardware systems architect to define architecture strategy for on-device AI in wearables, AR/VR devices. You will shape compute and memory hierarchies, camera/IP pipelines, and SoC interfaces, guiding cross-functional teams toward energy-efficient, scalable solutions.

You will lead multi-year roadmaps, evaluate trade-offs, and build models to forecast performance under real AI workloads.