Staff, GPU Performance Engineer

Samsung•San Jose, CA

18h•Onsite

About The Position

Samsung Austin Research and Development Center (SARC) and Advanced Computing Lab (ACL) are building a center of excellence for Intellectual Property (IP) applied to high-performance computing devices. We are seeking a highly skilled GPU Performance Engineer to join our team, responsible for workload analysis, benchmarking, and performance optimization of our GPU architecture. The successful candidate will play a critical role in ensuring our GPU performs well on a wide range of common use cases, driving the success of our GPU technology. This is an exciting opportunity to work on cutting-edge graphics technology and collaborate with cross-functional teams to analyze and optimize GPU performance.

Requirements

6+ years of experience with a Bachelor's degree in Computer Science/Computer Engineering/relevant technical field, or 4+ years of experience with a Master's degree, or 2+ years of experience with a PhD.
Strong understanding of 3D graphics pipelines, including render pipelines and game engines.
Experience on ML workload analysis and development.
Familiarity with graphics APIs, such as Vulkan.
Knowledge of performance analysis tools and methodologies.
Proficient programming skills in languages like Python and C++.
Excellent analytical and problem-solving skills, with the ability to identify and optimize performance bottlenecks.
Strong collaboration and communication skills, with experience working with cross-functional teams.
Passion for analyzing and optimizing GPU performance, with a drive to deliver high-quality results.

Nice To Haves

Familiarity with GPU architecture and design.
Familiarity with scripting languages and automation frameworks.
Experience working in a fast-paced, dynamic environment, with a focus on innovation and continuous improvement.

Responsibilities

Conduct in-depth workload analysis and benchmarking to identify performance bottlenecks and areas for optimization.
Collaborate with the workload and PPA teams to perform bottleneck analysis and performance attainment, providing valuable insights to inform GPU architecture and design decisions.
Develop and maintain benchmarking tools and scripts to measure GPU performance on various workloads, including 3D graphics, gaming, and ML applications.
Analyze and optimize GPU performance on multiple benchmarks, ensuring our GPU meets or exceeds industry standards.
Work closely with cross-functional teams, including software and hardware engineering, to identify and resolve performance-related issues.
Stay up-to-date with industry trends and emerging technologies, applying this knowledge to continuously improve GPU performance and competitiveness.
Develop and run benchmarks to characterize system performance and identify areas for improvement.
Stay up-to-date with the latest developments in graphics technology, including new APIs, tools, and methodologies.