Software Development Engineer, AI Workload Optimization

What you'll do

• Define and drive the end-to-end software optimization strategy for top-tier AI customers.
• Lead the profiling, analysis, and tuning of large-scale models like LLMs and Diffusion models.
• Partner with hyperscalers to deliver tailored architectural wins and software optimizations for unique workload requirements.
• Collaborate across hardware and compiler teams to influence future silicon features based on AI trends.
• Drive the development of advanced tools for performance estimation, modeling, and automated reporting.
• Act as a technical ambassador in industry forums and open-source communities.
• Mentor and inspire the next generation of AMD’s technical leaders and engineers.

What we're looking for

• Deep software development experience in a high-level technical leadership role (preferred).
• Deep expertise in AI Frameworks (PyTorch, JAX, vLLM, SGLang) and the ROCm software stack (preferred).
• Proven history of optimizing distributed inference and training at scale across multi-node/multi-GPU environments (preferred).
• Mastery of performance profiling tools (e.g., TorchProfiler, ROCm Profiler, Nsight) and hardware-level performance modeling (preferred).
• Strong understanding of modern model architectures and optimization techniques like quantization and FlashAttention (preferred).
• Demonstrated ability to drive cross-functional initiatives in fast-paced, ambiguous environments (preferred).
• Master’s degree or Bachelor’s degree in computer science, Electrical Engineering, or a related field, or equivalent experience (preferred).
• Demonstrated research or applied experience in AI/ML, including deep learning or model training/inference optimization (preferred).