GPU HPC Software Fellow — Remote

AMD; Austin (TX); On-site; USD 200,000 - 260,000; Full time

Job summary

AMD in Austin, TX is seeking a High Performance and Scientific Computing Fellow to lead HPC GPU libraries within the ROCm software platform. This technical leadership IC role focuses on deep expertise across math algorithms, GPU performance, and distributed systems, driving innovation across multiple AMD GPUs.

You will collaborate in a distributed agile environment, mentor senior engineers, and engage in external benchmarks and technical engagements to advance ROCm and AI applications.

Qualifications

• In-depth understanding of mathematical algorithms for dense and sparse linear algebra.
• Experience with direct and iterative solvers.
• Experience designing, implementing, debugging, and optimizing parallel algorithms on class-leading supercomputers.
• Knowledge of important HPC algorithms and libraries.
• Strong background developing applications and libraries in C++, C and Fortran.
• Familiarity with GPU software development and optimization using HIP, CUDA, or OpenCL and distributed programming with MPI and/or SHMEM.
• Understanding of CPU and GPU architectures and low-level optimization techniques including assembly programming and vectorization.
• In-depth knowledge of best-practices in software development, including testing, profiling, debugging, documentation, version control, issue tracking, and planning.

Responsibilities

• Define technical vision and drive software strategy across AMD ROCm HPC libraries.
• Lead performance analysis, tuning, and algorithmic innovation across HPC libraries.
• Provide technical mentorship to senior engineers and influence best practices across the organization
• Communicate complex technical findings and recommendations to senior leadership and stakeholders.
• Represent AMD in external technical forums, benchmarks, and customer engagements
• Work with key technical experts across AMD and with our partners and customers to improve ROCm HPC and AI applications, libraries, and tools.

Skills

HPC algorithms

Dense linear algebra

Sparse linear algebra

Parallel algorithms

C++, C, Fortran

HIP / CUDA / OpenCL

MPI / SHMEM

CPU/GPU architectures

Performance tuning

Education

BSc/BE in Computer Science, Software Engineering, Electrical Engineering, Applied Mathematics

MS/PhD preferred

Tools

Git

Job description

AMD in Austin, TX is seeking a High Performance and Scientific Computing Fellow to lead HPC GPU libraries within the ROCm software platform. This technical leadership IC role focuses on deep expertise across math algorithms, GPU performance, and distributed systems, driving innovation across multiple AMD GPUs.

You will collaborate in a distributed agile environment, mentor senior engineers, and engage in external benchmarks and technical engagements to advance ROCm and AI applications.