below marketmost similar roles pay hereabove market
This role pays more than
89%
of similar roles. Most pay
$187,850–$235,750
— the blue band above.
At the midpoint, this role pays about
$255k
versus about
$212k
for comparable roles.
Based on 240 similar postings.
Employer
About Amd
AMD (Advanced Micro Devices) is a semiconductor company that develops high-performance processors, graphics cards, and adaptive computing solutions for gaming, data centers, and embedded markets. Industry: Semiconductors
Amd currently has
500 open roles
on FindRole.
Listed pay typically runs
$172,000–$258,000
across 500 roles with salary data.
The Senior GPU Performance Engineer joins the team to optimize AI workloads and guide the evolution of next-generation AMD Instinct GPU architectures. This role involves performing deep GPU kernel-level performance analysis to identify microarchitectural bottlenecks in compute pipelines, memory hierarchy, and instruction execution. You will drive low-level kernel optimizations for foundation model workloads, including transformers and diffusion models, across multi-node systems. Key responsibilities include root-causing performance gaps using GPU performance counters, thread traces, and ISA/assembly analysis while collaborating with kernel, compiler, and distributed systems teams. Required skills include proficiency in C++, Python, CUDA, and HIP/ROCm. You must possess a deep understanding of GPU microarchitecture, SIMD/SIMT scheduling, and experience with frameworks like PyTorch, JAX, Megatron-LM, and communication libraries like NCCL/RCCL.
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 hierarchy.
Root-cause performance gaps using GPU performance counters, thread traces, and ISA/assembly analysis.
Deliver low-level kernel optimizations for foundation model workloads.
Develop and maintain benchmarks and microbenchmarks representative of AI workloads.
Provide microarchitecture-level performance insights to inform hardware and software co-design decisions.
Present performance findings to cross-functional teams and leadership to shape product roadmaps.
What we're looking for
MS or PhD in Computer Science, Computer Engineering, or a related technical field.
Strong hands-on experience in GPU kernel-level performance analysis and low-level optimization using CUDA, HIP/ROCm, or equivalent technologies.
Deep understanding of GPU microarchitecture, including execution pipelines, SIMD/SIMT scheduling, registers, memory hierarchy, caches, and interconnects.
Experience using performance counters, thread traces, profilers, and ISA/assembly analysis to root-cause GPU kernel performance bottlenecks.
Hands-on experience optimizing performance-critical GPU kernels and developing targeted microbenchmarks or reproducer kernels.
Proficiency in C++ and GPU kernel programming, with Python experience for performance analysis and automation.
Advanced Linux OS, container technologies such as Docker, and Git/GitHub skills.
Familiarity with AI workloads, AI frameworks, distributed computing, and communication libraries such as PyTorch, JAX, Megatron-LM, NCCL/RCCL, and MPI.
CUDA
Python
C++
PyTorch
TensorFlow
JAX
NVIDIA Nsight Systems
Linux perf
InfiniBand
NVLink
RoCE
NCCL
MPI
Docker
Kubernetes
SLURM
HPC
AI
ML
Shell Scripting