Skip to main content
AMD

Software Development Engineer - AI Workload Optimization

AMD Bellevue, WA, United States Full-time 6 months ago
Embedded & Systems Software

Originally posted June 5, 2026 by the employer. Relisted by the employer on October 28, 2026.

About the role

As a Fellow in the AI Software group, you are accountable for defining and driving the end-to-end software optimization strategy across the software stack. You will align architecture, customer engagement, and software engineering to tune ROCm, compilers, and high-level AI frameworks for demanding AI workloads.

What you'll do

  • Set the technical vision and roadmap for workload optimization across the AI software stack.
  • Lead the profiling, analysis, and tuning of large-scale models, including LLMs, Diffusion, Multimodal, and MoE architectures.
  • Partner with customers and hyperscalers to evaluate workload requirements and deliver architectural improvements and software optimizations.
  • Collaborate across hardware architecture, compiler, and framework teams to guide future silicon features based on AI workload trends.
  • Guide the development of tools and frameworks for performance estimation, modeling, and automated reporting.
  • Serve as a technical ambassador in industry forums and open-source communities while mentoring technical leaders and engineers.

What you'll need

  • Software development experience including service in a high-level technical leadership role, such as Fellow or equivalent.
  • Deep knowledge of AI hardware architecture, software optimization, and mapping model architectures to low-level software.
  • Experience solving performance bottlenecks across the software stack from compilers to AI frameworks.
  • Demonstrated background defining strategic technical roadmaps and engaging with key customers and engineering teams.

Nice to have

  • Expertise in AI frameworks such as PyTorch, JAX, vLLM, and SGLang, alongside the ROCm software stack.
  • Experience optimizing distributed inference and training at scale across multi-node/multi-GPU environments.
  • Experience with performance profiling tools such as TorchProfiler, ROCm Profiler, or Nsight, and hardware-level performance modeling.
  • Understanding of modern model architectures (Transformer, Attention, KV Cache) and optimization techniques including quantization, speculative decoding, and FlashAttention.
  • PhD or Master’s degree in Computer Science, Electrical Engineering, or a related field, or equivalent experience.
  • Demonstrated research or applied experience in AI/ML, including deep learning, model training/inference optimization, large language models, or computer vision.

Skills: AI workload optimization, ROCm, PyTorch, LLMs, distributed inference

More semiconductor jobs: AMD jobs

Market context

Tracked in our index since 6 Jun 2026. This is our observation date, not the employer posting date. Specialty: Infrastructure/Platform Software (GPU Software Stack). 334 active roles in this specialty at 26 employers in our index, as of 22 Nov 2026.

How we counted: postings read from employer career sites. How we count

Apply now
Bellevue, WA, United States
On-site
Full-time
6 months ago

Share this job