This listing doesn't post a salary. Most similar roles pay
$177,250–$235,750.
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
As a Fellow GPU Performance Optimization Engineer at our Models and Applications team, you will lead the optimization of large-scale AI training workloads on AMD GPUs, focusing on single-node and multi-node environments. Your daily tasks include identifying and resolving system bottlenecks across compute, memory, and communication channels to enhance scalability and efficiency through advanced profiling and benchmarking techniques. You will collaborate with hardware, compiler, and framework teams to influence the design of next-generation GPU architecture and software stacks, contributing to open-source projects aimed at improving performance on AMD platforms. Ideal candidates possess deep expertise in GPU architecture, distributed systems, and ML workloads, along with proficiency in Python, C++, CUDA, or HIP, and experience with frameworks like PyTorch and TensorFlow. This role demands a strong understanding of communication libraries such as NCCL/RCCL and the ability to drive impactful optimizations across various layers of the software stack.
Remote (San Jose, CA)13 days ago
$167,800–$251,800
Python
C++
Vulkan
3D graphics pipelines
GPU architecture
performance analysis tools
ML workload analysis
scripting languages
automation frameworks
CI/CD
Python
PyTorch
C++
ROCm
HIP
AMD Instinct GPUs
Distributed training
Multi-GPU/multi-node
SFT
LoRA
RL-based training
torch.distributed
FSDP
ZeRO
Distributed systems
Collective communication libraries
CI/CD