Platform Emulation Software Engineer - DC GPU

Overview As Platform Emulation Software Engineer, you contribute to pre-silicon verification for AMD’s Data Center GPU lineup. You design GPU applications in CUDA/C++ and build tools to speed up emulation debugging, benchmarks, and data analysis. You’ll collaborate across teams to support Instinct ML products for supercomputers and data centers, tackling performance and verification challenges at scale. This role blends software engineering with hardware emulation to shape high-performance, reliable GPU platforms. ResponsibilitiesDesign and implement GPU applications in CUDA/HIP to enhance pre-silicon verificationDevelop tools and automation to improve debugging efficiency on emulationRun and collect data for analysis on high-end emulators and simulation modelsDevelop scripts/tools to parse and analyze data from emulation runsRun and collect functional and performance data for AI/ML workloadsCollaborate with senior engineers to debug hardware-related failures and performance issues on emulationAttend weekly meetings, provide status updates, and present technical findings Key requirementsStrong knowledge of computer hardware architecture (GPU/CPU, memory hierarchy, interconnects, caches)Excellent programming skills in C, C++PythonTclExperience or understanding of Shared memory concurrent programmingRelaxed memory modelsCache coherencyWorking knowledge of Linux/Unix environments and shell scriptingKnowledge of boot flow (boot code, BIOS, device drivers, OS)Excellent oral and written communication skillsWillingness to learn and think outside the boxexcellent communicationcross-collaborationproblem-solving mindsetCUDA/HIP GPU programmingPython scriptingC/C++ programming