GPU Kernel Development Engineer - Machine Learning

AMD; Calgary; On-site; USD 126,000 - 190,000; Full time

Job summary

An innovative company is seeking a GPU Kernel Development Engineer to enhance machine learning capabilities through high-performance GPU kernel generation. In this role, you will design and implement critical components that support advanced tensor operations, collaborating with various teams to optimize performance and enhance the AMD Radeon Open Ecosystem. Your expertise in C++ and GPU code optimization will be pivotal in driving the next generation of computing experiences. This is an exciting opportunity to contribute to cutting-edge technology in a collaborative and inclusive environment.

Qualifications

• Experience in writing and optimizing GPU code.
• Understanding of compiler fundamentals and low-level optimization.

Responsibilities

• Design and implement GPU kernel generator for machine learning libraries.
• Analyze GPU kernel performance and identify optimization opportunities.
• Collaborate with teams to improve ROCm applications and libraries.

Skills

GPU Code Optimization

C++ Development

Machine Learning

Software Engineering Methodologies

Problem-Solving

Education

Bachelor’s or Master’s degree in Applied Mathematics

Bachelor’s or Master’s degree in Computer Science

Bachelor’s or Master’s degree in Computer Engineering

Bachelor’s or Master’s degree in Electrical Engineering

Tools

Version Control

Profiling Tools

Debugging Tools

Job description

GPU Kernel Development Engineer - Machine Learning

Join to apply for the GPU Kernel Development Engineer - Machine Learning role at AMD.

This range is provided by AMD. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.

Base pay range

$126,160.00/yr - $189,240.00/yr

What You Do at AMD Changes Everything

We care deeply about transforming lives with AMD technology to enrich our industry, communities, and the world. Our mission is to build products that accelerate next-generation computing experiences—data centers, AI, PCs, gaming, and embedded systems. We foster a culture of innovation, collaboration, humility, and inclusiveness.

The Role

You will develop a high-performance GPU kernel generator to support machine learning tensor operations with layer fusion. You will collaborate with teams across AMD involved in machine learning and math libraries, implementing primitives within the AMD Radeon Open Ecosystem (ROCm).

The Person

We seek a talented library developer passionate about deep learning performance, eager to learn, and innovative in problem-solving.

Key Responsibilities

• Design and implement AMD's GPU kernel generator used in various high-performance machine learning libraries and frameworks.
• Analyze GPU kernel performance and identify optimization opportunities.
• Develop optimization and analysis passes for GPU kernel graph representations.
• Collaborate with AMD teams, partners, and customers to improve ROCm applications, libraries, tools, and hardware.
• Produce high-quality code and documentation following open-source best practices.
• Apply software engineering methodologies for robust, maintainable code.
• Build technical relationships with peers and partners.

Preferred Experience

• Hands-on experience in writing and optimizing GPU code.
• Proficiency in modern C++ application and library development.
• Understanding of compiler fundamentals: ASTs, control flow graphs, data flow analysis, IR, target lowering.
• Experience with testing, profiling, debugging, documentation, version control, issue tracking.
• Knowledge of low-level optimization, assembly programming, and vectorization.

Academic Credentials

• Bachelor’s or Master’s degree in Applied Mathematics, Computer Science, Computer Engineering, Electrical Engineering, or related fields.

Location

Calgary, AB

Additional Info

Benefits are detailed in AMD benefits at a glance. AMD is an equal opportunity employer and encourages applications from diverse candidates. We are committed to accommodating applicants' needs throughout the recruitment process.