AMD is seeking a Software Development Engineer to join the AI Developer Tools team, focusing on designing and developing advanced GPU Debugging tools for HPC, ML, and AI workloads. The role involves contributing to the ROCm ecosystem by building robust debugging solutions that enhance AMD GPU capabilities. Candidates should be passionate about software engineering and performance optimization, with a strong foundation in C++ and computer architecture. Collaboration and effective communication across teams are essential for success in this position.

• Strong proficiency in C++ and object-oriented programming
• Experience with GDB, LLDB and other debug tools
• Familiarity with GPU programming models such as HIP, OpenCL, or CUDA
• Understanding of GPU architecture and system-level performance concepts
• Experience with multithreading and concurrency in modern C++
• Knowledge of Linux development environments; Windows experience is a plus
• Familiarity with ROCm ecosystem and tools is highly desirable
• Experience with Git-based workflows and debugging tools
• Strong problem-solving skills and ability to work independently and in a team

• Design, develop, and maintain ROCm Debugger components for GPU debugging
• Collaborate with architecture, driver, and runtime teams to enable profiling for next-generation AMD GPUs involved in Pre Silicon and Post Silicon activities
• Implement new features and APIs to enhance debugging capabilities for AI and HPC workloads
• Optimize profiling tools for accuracy, scalability, and minimal overhead
• Debug and resolve issues in profiling workflows and improve tool reliability
• Participate in hardware bring-up and ensure profiling support for new ASICs
• Stay current with GPU architecture advancements and integrate them into ROCm profiling tools
• Contribute to documentation and developer resources for ROCm Debugger

• AMD provides a competitive 'Total Rewards' package that focuses on financial growth, health, and work-life balance.