GPU Software Engineer - GPU Libraries

WHAT YOU DO AT AMD CHANGES EVERYTHING   At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond.   Together, we advance your career.    THE ROLE : As Senior Member of Technical Staff in the GPU Libraries group, you will help advance the strategy and execution across libraries that are part of the  AMD Radeon Open Ecosystem (ROCm)   ecosystem. As part of the larger  ROCm  libraries teams,  you will work cross-functionally with a team of talented computer scientists, software developers, and applied mathematicians working on GPU libraries for  high performance  computing and machine learning workloads.       THE PERSON : You are a strong technical engineer who thrives in complex, evolving environments. You have hands ‑ on experience enabling software on GPUs and are comfortable working across abstraction layers — from architecture concepts to implementation and debugging.   You enjoy collaborating with hardware, firmware, and software teams, and you are effective at translating architectural ideas into practical software solutions. You seek clarity, learn quickly from early data, and contribute constructively when requirements are incomplete.   You grow influence through technical execution, collaboration, and mentoring, and you are motivated to expand your architectural scope over time.

Work collaboratively across library teams to design, implement,  validate , and deliver key software library capabilities, ensuring successful integration with GPU kernels into broader systems. Provides significant technical inputs to the software roadmap.    Provides input to architecture, design, and documentation efforts as they arise across teams. Works closely with senior engineering staff to guide technical execution within library teams on broad and complex technical challenges.    Collaborate with principal members of staff to develop the best technical designs and approaches that holistically consider constraints, performance, and roadmap commitments. Execute, and report progress against project plans and delivery commitments.    Proactively  identifies  gaps and inconsistencies at project scope and develops plans to remediate in collaboration with library owners and engineering principal colleagues.    Engages in mentorships with senior and principal staff and  champion  internal  best-practice s  as part of the regular software development lifecycle in an agile environment.

H ands-on experience with  C++ ,  with relevant  applied experience using CUDA, HIP,  OpenMP, MPI,  or OpenCL  for accelerated computing on CPUs and GPUs.  Familiarity with other programming languages like Python  and AI/ML  Frameworks.   Experience  contributing to technical and high-performance software systems supported by  continuous improvement ,  regression  and performance management  systems ,   and  software  deployment and orchestration management   (Jenkins/Docker/Kubernetes/numerical methods and analysis).   Experience with open-source software development including collaboration with community maintainers and  submitting  contributions , and various lifecycle methodologies such as Agile, Scrum, Kanban.   Knowledge of professional software engineering practices and best practices for the full software development life