Fellow, AI Workload Optimization

Advanced Micro Devices, Inc•San Jose, CA

About The Position

AMD is seeking a technical leader to join its AI Software group. The Fellow will define and drive the end-to-end software optimization strategy to achieve industry-leading performance for top-tier customers. Working across architecture, customer engagement, and software engineering, the role will optimize AMD’s software stack—including ROCm, compilers, and high-level AI frameworks—to maximize performance on demanding AI workloads.

Requirements

Deep software development experience and experience in a high-level technical leadership role (Fellow or equivalent).
Deep expertise in AI frameworks such as PyTorch, JAX, vLLM, and SGLang, and in the ROCm software stack.
Proven history of optimizing distributed inference and training at scale across multi-node and multi-GPU environments.
Mastery of performance profiling tools such as TorchProfiler, ROCm Profiler, and Nsight, and hardware-level performance modeling.
Strong understanding of modern model architectures, including Transformer, Attention, and KV Cache, and optimization techniques such as quantization, speculative decoding, and FlashAttention.
Demonstrated ability to drive cross-functional initiatives in fast-paced, ambiguous environments.
PhD or Master’s degree in Computer Science, Electrical Engineering, or a related field, or equivalent experience.
Demonstrated research or applied AI/ML experience, including deep learning, model training or inference optimization, large language models, or computer vision.

Nice To Haves

PhD or Master’s degree in Computer Science, Electrical Engineering, or a related field, or equivalent experience.
Research or applied experience in AI/ML, including deep learning, model training or inference optimization, large language models, or computer vision.

Responsibilities

Set the technical vision and roadmap for workload optimization across the AI software stack.
Lead profiling, analysis, and tuning of large-scale LLM, diffusion, multimodal, and MoE models for performance on AMD hardware.
Partner with top customers and hyperscalers to understand workload requirements and deliver tailored architectural improvements and software optimizations.
Collaborate with hardware architecture, compiler, and framework teams to influence future silicon features based on AI workload trends.
Drive development of tools and frameworks for performance estimation, modeling, and automated reporting.
Represent AMD as a technical ambassador in industry forums and open-source communities.
Mentor and inspire AMD technical leaders and engineers.