Software Design Engineer, GPU Kernel Optimization

Amd

Confirmed live yesterday High trust

Quick summary

Work type: On-site
Location: San Jose, CA
Salary: $194,400–$291,600 / yr
Posted: 12 days ago
Freshness: Confirmed live yesterday
Closes: Oct 14, 2027
Nearby: 99+ roles within 25 mi

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $214k

This role $243k

$135k $308k

below market most similar roles pay here above market

This role pays more than 78% of similar roles. Most pay $188,562–$238,700 — the blue band above. At the midpoint, this role pays about $243k versus about $214k 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 496 open roles on FindRole.

Listed pay typically runs $172,000–$258,000 across 496 roles with salary data.

Most-posted roles

View all roles at Amd

At a glance

TL;DR · Software Design Engineer, GPU Kernel Optimization

Role Posting Log in to save

As a senior technical member of the team, the Software Design Engineer - GPU Kernel Optimization will design, develop, and optimize high-performance GPU kernels for LLM and other ML models. The role involves analyzing performance bottlenecks to maximize compute efficiency, memory bandwidth utilization, and overall GPU performance across current and next-generation platforms. Key responsibilities include architecting AI workloads, performing deep performance characterization of cache hierarchies and kernel scheduling, and developing compiler-level optimizations. The candidate will utilize C++, Python, HIP, CUDA, LLVM, and MLIR to build scalable solutions and AI-powered coding agents for kernel generation. This position focuses on solving technical challenges in GPU compute, memory hierarchy, and synchronization to improve end-to-end AI system performance for quantized models and emerging AI workloads.

Skills

GPU Programming C++ Python HIP CUDA LLVM MLIR GPU Kernels Performance Analysis Quantized Models LLM Code-Generation System Software Development

What you'll do

Design, implement, and optimize high-performance GPU kernels for LLMs and other ML models.
Lead the optimization of quantized models and emerging AI workloads for AMD GPU architectures.
Perform deep performance characterization to identify and eliminate bottlenecks in compute, memory, and cache.
Develop compiler-level optimizations and code-generation techniques using LLVM and MLIR.
Build AI-powered coding agents and automation workflows for kernel generation, benchmarking, and validation.
Provide technical leadership by defining goals, scoping projects, and owning development efforts independently.
Collaborate with architecture, compiler, and framework teams to develop scalable GPU performance solutions.

What we're looking for

Bachelors or Masters degree in computer engineering, computer science, or a related field.
Experience in GPU programming, performance analysis, and system software development.
Experience designing, implementing, and optimizing high-performance GPU kernels for LLM and ML models.
Experience with compiler-level optimizations and code-generation using LLVM and MLIR.
Strong C++ and/or Python skills (preferred).
Experience developing GPU kernels using HIP, CUDA, C/C++, or similar technologies (preferred).
Solid understanding of GPU compute, memory hierarchy, cache behavior, and synchronization (preferred).
Strong analytical/problem-solving skills and ability to independently drive tasks to completion (preferred).

Save