This software engineer role at AMD focuses on driving the strategy, architecture, optimization, and tooling for AI Pre-training and Distributed Inference Performance on AMD GPUs. The position requires collaboration across hardware architecture, AI frameworks, and developer tools to enhance performance analysis and optimization. The ideal candidate will have expertise in network, NIC, and GPU hardware architecture, as well as experience in performance modeling and AI frameworks. This role is essential for shaping the future of AI acceleration and optimizing performance across multiple generations of AMD GPUs.

• Deep knowledge of Network, NIC, and GPU hardware architecture.
• Experience in software optimization and performance modeling.
• Hands-on experience with AI frameworks such as PyTorch, JAX, vLLM, and SGLang.
• Strong technical leadership skills and ability to work collaboratively with cross-functional teams.
• A PhD or master's degree in computer science, electrical engineering, or a related field.

• Help with strategy and roadmap for AMD Collectives and Network optimizations.
• Provide guidelines to customers on efficient network load-balancing, workload scheduling, and model sharding strategies.
• Conduct performance tuning, profiling, and analysis of large-scale models for various AI applications.
• Participate in hardware-software co-design for future hardware optimizations.
• Develop and improve frameworks, tools, and infrastructure for performance estimation and reporting.
• Communicate and present performance analysis results to stakeholders and senior leadership.
• Collaborate across teams to identify opportunities and develop strategies.

• AMD provides a competitive 'Total Rewards' package that focuses on financial growth, health, and work-life balance.