Fellow, AI Workload Optimization in San Jose, California | Advanced Micro Devices, Inc

What you'll do

• Define and drive the end-to-end software optimization strategy for industry-leading performance.
• Lead profiling, analysis, and tuning of large-scale AI models to ensure optimal performance on AMD hardware.
• Engage with top-tier customers to understand unique workload requirements and deliver tailored optimizations.
• Influence future silicon features by collaborating across hardware architecture and software teams.
• Develop advanced tools and frameworks for performance estimation and automated reporting in the AI ecosystem.

What we're looking for

• Over 15 years of software development experience with at least 5 years in high-level technical leadership.
• Deep expertise in AI frameworks like PyTorch and ROCm software stack.
• Proven history of optimizing distributed inference and training across multi-node/multi-GPU environments.
• Mastery of performance profiling tools and hardware-level performance modeling techniques.
• Strong understanding of modern model architectures and optimization techniques including quantization, speculative decoding.
• Demonstrated ability to drive cross-functional initiatives in fast-paced, ambiguous environments.