Job requires a deep understanding workloads and usages of the AI Inference market covering Data Center to the Edge. The AI Solutions Architect must be able to translate usage requirements into workloads for modeling to analyze and develop the system and infrastructure level architecture and optimizations required for deployment of scalable AI/ML solutions.
Essential Duties and Responsibilities:
- Research and develop target workloads for various market segments for AI Inference
- Analyze the system level performance of these workloads on different AI HW and SW frameworks.
- Specify system level requirements for different target markets for performance, cost, and power optimized solutions
- Be the subject matter expert with respect to current and future trends in usages and workloads in the AI Inference domain.
- Collaborate with hardware and software teams to guide the development of next generation AI accelerators and software frameworks.