Senior Silicon Design Engineer, Hardware-Software Co-Design, GPU Compute and AI Compilers & Runtimes

Amd

Hybrid

Quick summary

Work type: Hybrid
Location: Washington
Posted: 82 days ago
Closes: Apr 6, 2027
Nearby: 99+ roles within 25 mi

Market check

Salary context

How this pay compares to similar roles

Similar $195k

$141k most similar roles pay here $252k

This listing doesn't post a salary. Most similar roles pay $173,850–$216,250.

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 56 open roles on FindRole.

Most-posted roles

View all roles at Amd

At a glance

TL;DR · Senior Silicon Design Engineer, Hardware-Software Co-Design, GPU Compute and AI Compilers & Runtimes

Role Posting Log in to save

The AMD AI Group seeks a Senior Silicon Design Engineer to co-design the hardware-software interface for AMD Instinct™ GPUs, working closely with hardware architects to model and evaluate how GPU microarchitecture interacts with AI frameworks and the ROCm™ software stack. Day-to-day responsibilities include building performance and power models that connect architectural decisions to real workload behavior, evaluating proposed hardware features against AI training and inference targets, and optimizing GPU kernels and compiler passes for AMD GPUs. The role involves deep collaboration across the Linux kernel DRM/GEM layer, ROCm™ runtime, IREE compiler, and AI frameworks like PyTorch and Triton, requiring expertise in C/C++, Python, CUDA/HIP, and knowledge of modern AI model architectures. Ideal candidates have 5+ years of industry experience at the hardware-software boundary, strong computer architecture skills, and proficiency with AMD Instinct GPU architectures and ROCm™ stack.

Skills

C C++ Python CUDA HIP Linux DRM/GEM ROCm IREE PyTorch Triton LLVM MLIR GPU HPC AI Compiler Performance Modeling System-Level Programming Kernel-Mode Drivers Memory Management Framework Internals Quantization Techniques Attention Mechanisms Mixture-of-Experts

What you'll do

Build performance and power models connecting GPU microarchitecture to software execution.
Analyze AI workloads against AMD Instinct™ microarchitecture to identify bottlenecks.
Evaluate proposed hardware features for impact on real-world workload performance.
Design and optimize compiler backend optimizations targeting AMD GPU microarchitecture.
Improve asynchronous execution in Linux kernel DRM/GEM subsystem for GPU compute.
Develop reproducible benchmarks to ensure consistent stack performance across changes.
Provide software feedback on next-generation Instinct™ GPU designs for workloads.

What we're looking for

5+ years of industry experience at the intersection of GPU hardware and AI software.
Strong foundation in computer architecture, including memory models and GPU microarchitecture.
Proficiency in C/C++ for system-level work and Python for tooling and analysis.
Experience with AMD Instinct GPUs and ROCm stack, including Linux kernel DRM/GEM subsystems.
Expertise in performance modeling and optimization of AI frameworks like PyTorch and Triton.