Distinguished Technologist - AI Model Performance Architect
Texas, Palo Alto
Workplace: OnsiteFull timeUSD 190,000 - 274,000 annuallyFunction: Hardware, Embedded & Systems EngineeringExperience: 12+ yearsEducation: bachelorsSkills: ["Effective communication","Results orientation","Learning agility","Digital fluency","Customer centricity"]Bridge system memory architecture with AI model behavior to improve performance via HW/SW co-design and workload-aware tuning. Develop AI workload optimization strategies to reduce startup time, enhance inferencing efficiency, and minimize memory needs. Analyze bandwidth/latency bottlenecks, model performance across CPU/GPU/NPU, and simulate/optimize execution details like initialization, caching, and KV reuse. Lead R&D, influence long-term roadmaps, and partner across ML and hardware engineering teams.
Loading
Loading job details...
Preparing the role view and application actions.

