Application Developer / Engineer 3

Description: Senior Kernel/ROCm Developer:
We are looking for a self-motivated and dynamic Senior Kernel/ROCm Developer with strong hands-on experience in Linux kernel, device driver, GPU compute, and ROCm software development. The ideal candidate will have 7+ years of relevant industry experience, a bachelors or master’s degree in computer science, Computer Engineering, Electrical Engineering, or a related field, and the ability to independently drive complex technical issues from analysis through resolution. This role involves developing, debugging, optimizing, and maintaining kernel-level and ROCm components for AMD GPU platforms while collaborating closely with cross-functional hardware, firmware, compiler, runtime, and software teams.
Key Responsibilities:
• Design, develop, debug, and maintain Linux kernel, GPU driver, KFD, and ROCm-related components for AMD GPU platforms.
• Analyze, reproduce, root-cause, and resolve complex kernel, driver, ROCm runtime, and GPU compute issues across software and hardware boundaries.
• Collaborate with hardware, firmware, compiler, runtime, validation, and application teams to enable robust GPU compute functionality and platform bring-up.
• Use advanced debugging and profiling tools such as kgdb, ftrace, tracepoints, perf, dmesg, crash dumps, ROCm tools, and GPU diagnostics to troubleshoot issues.
• Drive technical investigations independently, propose design improvements, and deliver high-quality fixes with strong ownership and accountability.
• Conduct performance analysis and optimization for kernel, driver, ROCm, and GPU compute workloads to improve stability, scalability, and efficiency.
• Participate in architecture discussions, design reviews, code reviews, and open-source-style development practices while maintaining high coding standards.
• Stay current with Linux kernel, GPU architecture, ROCm, heterogeneous compute, and open-source technology trends.
Required Skills and Qualifications:
• Bachelor’s or master’s degree in computer science, Computer Engineering, Electrical Engineering, or a related technical field.
• Minimum 7+ years of relevant experience in Linux kernel development, device driver development, ROCm, GPU compute software, or related system software areas.
• Strong understanding of Linux kernel architecture, device drivers, memory management, scheduling, synchronization, and kernel programming concepts.
• Hands-on familiarity with AMD GPU architecture, KFD, ROCm software stack, GPU compute, heterogeneous memory management, or similar accelerator technologies.
• Strong programming expertise in C and C++, with proven debugging experience in Linux-based system software environments.
• Experience with performance profiling, bottleneck analysis, and optimization of kernel, driver, runtime, or GPU compute workloads.
• Ability to work independently in a fast-paced environment, take initiative, and adapt quickly to changing technical priorities.
• Excellent analytical, problem-solving, and debugging skills with a strong bias for ownership and timely execution.
• Strong verbal and written communication skills, with the ability to collaborate effectively across geographically distributed teams.
Preferred Skills:
• Prior experience with KFD, DRM, amdgpu, ROCm runtime, HIP, HSA, or GPU compute driver development.
• Experience contributing to upstream Linux kernel, open-source GPU drivers, ROCm components, or other community-driven software projects.
• Knowledge of GPU virtualization, memory management, PCIe, IOMMU, NUMA, power management, or platform bring-up is a plus.