Senior GPU Performance Engineer - AI Workloads

Advanced Micro Devices, Inc; Santa Clara (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Advanced Micro Devices, Inc. in Santa Clara, CA, seeks a GPU Performance Engineer to optimize AI workloads and push the performance of AMD Instinct GPUs.

You will analyze kernels, identify bottlenecks, and drive low-level optimizations across multi-node, multi-GPU systems. Collaborating with kernel, compiler, runtime, framework, and distributed systems teams, you will develop benchmarks and microbenchmarks, and communicate findings to drive hardware-software co-design for future AMD

Qualifications

• MS/PhD in CS, CE, or related field.
• Hands-on GPU kernel-level performance analysis and low-level optimization (CUDA/HIP/ROCm).
• Deep GPU microarchitecture knowledge: pipelines, SIMD, memory, interconnects.
• Experience using perf counters, traces, profilers, and ISA/assembly to root-cause bottlenecks.
• Proficient in C++ and GPU kernel programming; Python for automation.
• Linux, Docker, Git/GitHub skills.
• Familiar with AI workloads and frameworks (PyTorch, JAX, Megatron-LM, NCCL/RCCL, MPI).

Responsibilities

• Profile and optimize large-scale AI workloads across multi-node multi-GPU systems.
• Perform deep GPU kernel-level analysis to identify bottlenecks in compute pipelines and memory.
• Root-cause performance gaps using performance counters, traces, ISA/assembly, and microbenchmarks.
• Collaborate with kernel, compiler, runtime, framework, and distributed systems teams to improve performance.
• Develop and maintain benchmarks, microbenchmarks, and traces for foundation model workloads.
• Provide kernel- and microarchitecture-level performance insights to inform hardware/software co-design.

Skills

GPU kernel analysis

Low-level optimization

C++ and GPU kernel programming

Python for performance analysis

Linux

Docker

Git/GitHub

AI workloads familiarity

Education

MS or PhD in CS/CE

Tools

CUDA

HIP/ROCm

Performance counters

ISA/assembly analysis

Microbenchmarks

Reproducer kernels

Job description

ADVANCE YOUR CAREER. ADVANCE THE WORLD.

At AMD, we believe technology has the power to solve the world’s most important challenges. From advancing healthcare and scientific discovery to powering AI and the technologies people rely on every day, innovation at AMD is shaping the future.

Whether you’re redesigning next-gen processors, enabling AI breakthroughs, or bringing leading edge products to market, every role at AMD contributes to something bigger—technology that moves the world forward. Join us and, together, we’ll advance your career.

About the Role

We are seeking a GPU Performance Engineer to optimize AI workloads and guide the evolution of next-generation AMD Instinct GPU architectures. In this role, you will work across the software and hardware stack to perform deep GPU kernel-level performance analysis, identify microarchitectural bottlenecks, and drive low-level kernel optimizations for foundation model workloads on large-scale GPU systems. You will collaborate with kernel, framework, distributed systems, compiler/runtime, and hardware architecture teams to ensure our GPUs deliver industry-leading AI performance today while shaping the designs of tomorrow.

Key Responsibilities

1. Profile and optimize large-scale AI workloads, including transformers, multimodal models, diffusion models, and recommender systems, across multi-node, multi-GPU systems.
2. Perform deep GPU kernel-level analysis to identify bottlenecks in compute pipelines, memory hierarchy, instruction execution, synchronization, and data movement.
3. Root-cause performance gaps using GPU performance counters, thread traces, ISA/assembly analysis, and targeted microbenchmarks, and deliver low-level kernel optimizations.
4. Collaborate with kernel, compiler, runtime, framework, and distributed systems teams to improve kernel performance, scheduling, memory utilization, and system-level efficiency.
5. Develop and maintain benchmarks, microbenchmarks, and traces representative of foundation model and broader AI workloads.
6. Provide kernel- and microarchitecture-level performance insights to AMD Instinct GPU architecture teams, informing hardware/software co-design decisions for future architectures.
7. Present findings to cross-functional teams and leadership, shaping both software and hardware roadmaps.

Minimum Qualifications

1. MS or PhD in Computer Science, Computer Engineering, or a related technical field.
2. Strong hands-on experience in GPU kernel-level performance analysis and low-level optimization using CUDA, HIP/ROCm, or equivalent technologies.
3. Deep understanding of GPU microarchitecture, including execution pipelines, SIMD/SIMT scheduling, registers, memory hierarchy, caches, and interconnects.
4. Experience using performance counters, thread traces, profilers, and ISA/assembly analysis to root-cause GPU kernel performance bottlenecks.
5. Hands-on experience optimizing performance-critical GPU kernels and developing targeted microbenchmarks or reproducer kernels.
6. Proficiency in C++ and GPU kernel programming, with Python experience for performance analysis and automation.
7. Advanced Linux OS, container technologies such as Docker, and Git/GitHub skills.
8. Familiarity with AI workloads, AI frameworks, distributed computing, and communication libraries, such as PyTorch, JAX, Megatron-LM, NCCL/RCCL, and MPI.

Preferred Qualifications

1. Strong track record of delivering GPU kernel performance improvements through low-level hardware/software analysis and optimization.
2. Experience working across kernel, compiler/runtime, framework, distributed systems, and GPU architecture teams to resolve complex performance bottlenecks.
3. Experience analyzing large-scale AI workloads and translating workload-level performance gaps into actionable kernel, software-stack, or microarchitecture improvements.

This role is not eligible for visa sponsorship.

#LI-RL1

Benefits offered are described: AMD benefits at a glance.

AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.

AMD may use Artificial Intelligence to help screen, assess or select applicants for this position. AMD’s “Responsible AI Policy” is available here.

This posting is for an existing vacancy.