Principal AI Software Engineer

AMD AI Group Technical Leader

At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you'll discover the real differentiator is our culture.

We push the limits of innovation to solve the world's most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond. Together, we advance your career.

AMD AI Group is seeking a highly influential technical leader for OneROCm—driving a unified ROCm software stack across AMD's broad product portfolio, including Instinct, Radeon, Ryzen, Embedded, Game Consoles, and Autonomous Driving platforms. This is a rare opportunity to drive innovation, and help develop next-generation products(NPI) at company-wide scale. The ideal candidate will shape the end-to-end ROCm software and influence the full stack, spanning compilers, kernels, runtime, libraries, models, frameworks, and performance optimization layers.

The role also requires strong hardware/software co-design to maximize performance across diverse AMD products and workloads. The ideal candidate is expected to be highly hands-on and embrace agentic AI workflows.

You are a strong technical leader who is able to work across organizations, align architecture with product goals, and influence innovation and execution. You bring deep expertise in at least one major area of the stack, while also demonstrating the curiosity, adaptability, and technical breadth to learn new domains, grow their impact, and influence the broader ecosystem.

As a successful candidate, you are recognized for technical excellence, and the ability to deliver innovations through collaboration across silicon, system software, AI/ML frameworks, libraries, and application enablement teams.

Key responsibilities include:

• Hardware-Software Co-design:
  Collaborate across hardware architecture, compiler, math libraries, kernel and framework teams to influence future silicon features based on evolving AI workload trends.
• Strong Execution:
  Deliver innovations and roadmap for AI software stack across all AMD products, ensuring AMD remains the platform of choice for top-tier AI customers.
• Workload Performance Engineering:
  Lead the profiling, analysis, and tuning of large-scale models (LLMs, Diffusion, Multimodal, and MoE) to ensure "out-of-the-box" performance excellence on AMD hardware.
• Ecosystem Innovation:
  Drive the development of advanced tools and frameworks for performance estimation, modeling, and automated reporting.
• Customer Engagement:
  Partner with top customers and hyperscalers to understand their unique workload requirements and deliver tailored architectural wins and software optimizations.
• Community & Open Source:
  Mentor and inspire other engineers and contribute to ROCm Opensource.

Preferred experience includes:

• Knowledge in GPU architectures, basic knowledge of CPU architecture
• Experience in AI/ML software stack spanning compilers, kernels, runtime, libraries, models, frameworks, and performance optimization layers
• Understanding of GPU programming such as ROCm, CUDA, OpenCL, etc
• Experience in hardware/software co-design, building high-performance products across the full product lifecycle.
• Experience with operating systems (OS) and device driver development is a plus

Academic credentials:

• Undergrad degree required. Bachelor of Science, Masters, or PhD degree with emphasis in Electrical Engineering, Computer architecture, or Computer Science with relevant experience preferred

Location:

San Jose, other locations will be considered.