GPU Kernel Development Engineer - Fellow

Amd

Confirmed live today High trust

Quick summary

Work type: On-site
Location: Austin, TX
Salary: $231,360–$347,040 / yr
Posted: 54 days ago
Freshness: Confirmed live today
Closes: Sep 3, 2027
Nearby: 99+ roles within 25 mi

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $212k

This role $289k

$129k $370k

below market most similar roles pay here above market

This role pays more than 93% of similar roles. Most pay $187,850–$235,750 — the blue band above. At the midpoint, this role pays about $289k 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 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 · GPU Kernel Development Engineer - Fellow

Role Posting Log in to save

As a GPU Kernel Development Engineer - Fellow, you will join the team to define and drive the end-to-end software optimization strategy for top-tier customers. You will be responsible for GPU architecture feature design, API design, and deployment to achieve industry-leading performance. Your daily work involves performing external benchmarking, researching performance improvements, and analyzing the AI software stack to optimize GPU kernels. You will collaborate with hardware, compiler, and framework teams to influence future silicon features based on evolving workload trends. Key requirements include expertise in modern model architectures like Transformer, Attention, and KV Cache, alongside optimization techniques such as quantization, speculative decoding, and FlashAttention. You must possess deep knowledge of GPU architecture, algorithm development, and machine learning to deliver high-performance ROCm core software.

Skills

ROCm Machine Learning HPC GPU Architecture Transformer FlashAttention Quantization Speculative Decoding KV Cache Algorithm Development Performance Analysis Compiler Software Optimization AI Software Stack

What you'll do

Define and drive the end-to-end software optimization strategy to achieve industry-leading performance.
Design GPU architecture features, APIs, and deployment strategies for top-tier customers.
Perform external benchmarking and research to identify GPU kernel performance improvements.
Analyze and optimize GPU kernel performance across the entire AI software stack.
Partner with hyperscalers to deliver tailored architectural wins and software optimizations for unique workloads.
Influence future silicon features by collaborating with hardware, compiler, and framework teams.
Improve ROCm applications, libraries, and tools through technical collaboration with internal and external experts.

What we're looking for

Broad and deep experience in compute and machine learning software development is required.
Experience developing GPU kernels for high-performance ROCm core software is required.
Strong understanding of modern model architectures like Transformer and Attention is preferred.
Knowledge of optimization techniques like quantization, speculative decoding, and FlashAttention is preferred.
Excellent GPU architecture knowledge, performance analysis, and algorithm development experience is preferred.
Proven history of optimizing GPU kernels across the entire AI software stack is preferred.
Demonstrated ability to drive cross-functional initiatives in fast-paced, ambiguous environments is preferred.
A Bachelor’s, Master's, or PhD degree in Computer Science, Computer Engineering, or equivalent is preferred.

2+ yrs exp

Save