✦ Luna Orbit — AI & Machine Learning

Fellow, AI Software (Workload Optimization)

at Advanced Micro Devices

📍 San Jose, California, United States Unknown Posted March 14, 2026
Type Not Specified
Experience lead
Exp. Years 15+ years
Education Not specified
Category AI & Machine Learning

This role involves leading the development of software optimization strategies for AI workloads at AMD, focusing on hardware-software co-design and industry-leading performance for demanding AI applications.

  • Define AI software optimization strategy
  • Lead performance analysis of AI models
  • Engage with top AI customers
  • Influence silicon design
  • Mentor technical teams

The position requires expertise in AI hardware architecture, software performance tuning, and AI frameworks, with a focus on large-scale models like LLMs, Diffusion, and MoE, utilizing ROCm and compiler technologies.

The ideal candidate is a highly experienced AI hardware and software expert with 15+ years in AI architecture, performance optimization, and large-scale model deployment. They possess strong leadership skills, strategic vision, and industry engagement experience.

deep knowledge of AI hardware architecturesoftware optimizationperformance bottlenecksAI workloadsstrategic leadership
industry engagementopen-source communitiesmodel architecturesperformance analysis tools
ROCmAI frameworkscompilers
AI hardware architecturesoftware optimizationperformance bottlenecksAI workloadsROCmcompilersAI frameworksperformance tuninglarge-scale modelsLLMs
AI hardware architecturesoftware optimizationperformance bottlenecksAI workloadsROCmcompilersAI frameworksperformance tuninglarge-scale modelsLLMsDiffusionMultimodalMoE
communicationleadershipstrategic thinkingcollaborationinfluencementorship
Industry Technology
Job Function Lead AI software performance optimization and architecture strategy
Role Subtype AI & Machine Learning
Tech Domains Active Directory, Microsoft 365, Azure, Python, AI frameworks
AI hardware architecturesoftware optimizationperformance bottlenecksAI workloadsROCmcompilersAI frameworksperformance tuninglarge-scale modelsLLMsDiffusionMultimodalMoEperformance analysisindustry engagementopen-sourceleadershipstrategic roadmapmentorshipROC

Lack of deep AI hardware architecture knowledge, No experience with performance optimization, Less than 10 years experience, No leadership or mentorship background

Apply for this Position →

Get matched to jobs like this

Luna finds roles that fit your skills and career goals — no endless scrolling required.

Create a Free Profile