GPU/AI Application Platform Architect - San Jose
Core
Architecting, designing, and building high-performance, low-cost server and storage systems for GPU/AI LLM applications.
Role type
Senior IC GPU/AI Application Platform Architect
Builds
High-performance server and storage systems for AI/LLM workloads
Domain
Hardware infrastructure, GPU/AI systems, LLM technology
Deliverable
production ML models
Required skills
GPU/AI SoC and platform architecture, Interconnect Fabric, Memory sub-system, GPU/AI system application performance optimization, software hardware co-design, LLM model architecture, GPU/AI virtualization, deep learning architecture, distributed systems
Preferred skills
GPU/AI LLM platform architecture, application performance optimization design, software hardware co-design
Technologies
GPU, AI, LLM, SoC, Interconnect Fabric, Memory sub-system, virtualization, deep learning, distributed systems
Responsibilities
Track and evaluate new GPU/AI LLM technologies from industry and partners; Drive platform customization via performance optimizations and architecture explorations; Study and implement new GPU/AI LLM technology solutions; Evaluate GPU system performance under state-of-art LLM applications; Work with industry consortiums to investigate emerging technologies and standards; Setup POCs or prototypes with technology partners to evaluate new technologies or architectural designs.
