Staff Engineer, GPU System Engineer

Samsung•San Diego, CA

3d•Onsite

About The Position

Samsung, a world leader in advanced semiconductor technology, is founded on a simple philosophy – the endless pursuit of excellence will create a better world for all. At Samsung Austin Research and Development Center (SARC) and Advanced Computing Lab (ACL), we are building a center of excellence for Intellectual Property (IP) that is applied to high-performance computing devices (mobile, automotive, and other custom market segments) consumed by millions of people around the world. Come build with us! As a Staff GPU System Engineer, you will lead pre-silicon workload enablement, design and build verification infrastructure and automation framework for Samsung’s next-generation GPU and system-level IP. Your work will directly influence architectural validation, performance predictability, and pre-silicon SW feature verification by ensuring GPU designs meet architectural specifications and achieve the targeted performance expectations across architectural models, emulation, and silicon environments. In this high-impact individual contributor role, you will contribute to workload enablement for Architecture, HW, Emulation, SW and PPA teams, develop scalable automation and testing infrastructure. You will partner closely with GPU architecture, modeling, SW, and validation teams to provide enriched workload content to identify bottlenecks, debug driver & compiler issues, and help early architectural ideation and feature exploration. Leveraging your expertise in GPU architecture and advanced rendering knowledge, you architect and drive pre-silicon graphics workloads verification strategies, methodologies, and execution flows for graphics core and GPU subsystem validation. You develop and maintain workload capture and replay infrastructure, including workloads analysis, SW middle-ware development, utility tools, automation, and scalable testing framework to provide trace contents to Architecture, HW, SW, Emulation teams. You ensure technical excellence by analyzing, correlating, and debugging issues that could happen on Android system, Vulkan driver & compiler, Linux kernel, architecture specs, emulation, and silicon. You lead cross-functional collaboration with GPU architecture, Modeling, Design, Emulation, and Software teams to define critical workloads, debug functional issues, align workload behavior with architectural intent, and improve overall GPU efficiency and scalability. You inspire high performance by mentoring engineers, advancing pre-silicon driver & compiler verification methodologies, and fostering a culture of ownership, innovation, and continuous learning while staying ahead of emerging GPU architectures, graphics workloads, and AI/ML compute trends.

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 GPU architecture, graphics pipelines, compute workloads, and microarchitecture performance behavior.
Strong hands-on programming experience in C++ and Python within Linux development environments.
Experience developing Vulkan tests, profiling infrastructure, automation frameworks, and workload characterization methodologies.
Strong experience in analyzing and triaging issues in Android SW stack, Linux kernel in pre-silicon environments.
Familiarity with graphics and compute APIs such as OpenGL, Vulkan, OpenCL, or related GPU software stacks.
Excellent analytical and problem-solving skills, with the ability to identify bottlenecks, propose solutions and guide teams through implementation.
Excellent communication and collaboration skills, with the ability to navigate ambiguity and influence in a fast-paced, global team environment.

Nice To Haves

Experience with Android device debugging, Linux kernel development
Experience with Vulkan / OpenGL ES / OpenCL API programming or driver development
Familiarity with AI/ML, graphics rendering, or heterogeneous compute workloads
Experience with RTL verification, emulation, modeling, or post-silicon performance analysis

Responsibilities

Lead pre-silicon workload enablement, design and build verification infrastructure and automation framework for Samsung’s next-generation GPU and system-level IP.
Contribute to workload enablement for Architecture, HW, Emulation, SW and PPA teams, develop scalable automation and testing infrastructure.
Partner closely with GPU architecture, modeling, SW, and validation teams to provide enriched workload content to identify bottlenecks, debug driver & compiler issues, and help early architectural ideation and feature exploration.
Architect and drive pre-silicon graphics workloads verification strategies, methodologies, and execution flows for graphics core and GPU subsystem validation.
Develop and maintain workload capture and replay infrastructure, including workloads analysis, SW middle-ware development, utility tools, automation, and scalable testing framework to provide trace contents to Architecture, HW, SW, Emulation teams.
Analyze, correlate, and debug issues that could happen on Android system, Vulkan driver & compiler, Linux kernel, architecture specs, emulation, and silicon.
Lead cross-functional collaboration with GPU architecture, Modeling, Design, Emulation, and Software teams to define critical workloads, debug functional issues, align workload behavior with architectural intent, and improve overall GPU efficiency and scalability.
Mentor engineers, advance pre-silicon driver & compiler verification methodologies, and foster a culture of ownership, innovation, and continuous learning while staying ahead of emerging GPU architectures, graphics workloads, and AI/ML compute trends.