[Hiring] GPU Performance Engineer @Advanced Micro Devices, Inc

Role Description

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.

You:

• Are a performance‑focused GPU engineer to work at the intersection of low‑level GPU architecture, parallel algorithms, and real‑world workloads.
• Will dive deep into compute and shader performance, partnering closely with senior engineers to analyze, optimize, and scale GPU workloads across modern architectures.
• This is a hands‑on, technically rigorous role where curiosity, precision, and impact matter.

What You’ll Be Part Of:

• GPU performance optimization across HLSL compute shaders and/or CUDA / HIP kernels
• Deep analysis of modern GPU architectures, including warp/wavefront execution, occupancy, memory hierarchy, caches, and LDS/shared memory
• Design and evaluation of parallel algorithms, with careful attention to numerical stability and precision trade‑offs
• End‑to‑end performance analysis, including profiling, benchmarking, and root‑cause investigation using GPU performance tools
• Clear communication of performance findings and collaborative problem‑solving with graphics and compute teams

Qualifications

• Strong experience with HLSL and Direct3D 12
• Hands‑on experience with HIP and ROCm
• Expertise in GPU profiling and performance analysis
• Solid understanding of parallel algorithms and patterns
• Strong foundation in performance engineering fundamentals
• Advanced C++ (C++17/20) skills
• Experience with debugging, validation, and correctness testing
• Background in numerical computing and floating‑point behavior

Requirements

• Experience with additional GPU APIs (Nice to Have)
• Knowledge of shader compilation pipelines and intermediate representations (IRs) (Nice to Have)
• Exposure to ML or linear algebra acceleration (Nice to Have)
• Advanced GPU performance techniques (Nice to Have)
• Experience building tooling and automation (Nice to Have)
• Understanding of the graphics pipeline (Nice to Have)
• Experience across multiple platforms and architectures (Nice to Have)

Academics

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or equivalent

Benefits

• AMD benefits at a glance