> Markdown version of [/jobs/ext/131519-gpu-software-developer](https://www.wearedevelopers.com/jobs/ext/131519-gpu-software-developer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # GPU Software Developer - **Company:** Advanced Micro Devices, Inc. - **Location:** Austin, TX, United States - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Assembly Language, C++ (Programming Language), Nvidia CUDA, Computer Programming, Computer Engineering, Software Debugging, Field-Programmable Gate Array (FPGA), Python (Programming Language), Open Source Technology, OpenCL, Performance Tuning, Software Tools, Software Engineering, Information Technology, Code Restructuring - **Published:** May 19, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=9a5d5abb041c3ad9 ## About the Role * Possess excellent software skills in Python and C++ * Have low-level software optimization experience * Have strong desire and ability to solve problems quickly * Be able to schedule, and work on tasks independently * Have excellent written and verbal communication skills * Be flexible and accept new challenges, * 3+ years software development experience * Proficient in Python & C/C++ programming employing best software design practices * Experience working with large-scale software development projects and understanding of PC architecture * Proven experience in code optimizations for any architectures such as CPU/GPU/FPGA * GPU software development or validation involving HIP, CUDA, or OpenCL * Experience in SIMD vectorization is a plus * Experience in system-level performance evaluations and debugging * Ability to closely interact with architects, developers, and tuning teams to maintain and release production software * Great communication and teamwork skills, * Bachelor's or higher degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent ## Description The GPU libraries team, within the ROCm software ecosystem, develops software for the latest innovations that power the ultimate computing experience provided by our AMD Instinct GPUs. The highly tuned libraries are developed with C++, Python, HIP, and low-level GPU assembly programming involving large teams. To grow these libraries with rich features and support customers at scale, development must follow great software design principles while striving for simplicity, ease-of-maintenance, and extensibility. The successful candidate for this role will be an integral part of our GPU Matrix & Tensor operations team through modular and maintainable code development, code refactoring, debug, and performance optimizations. Relevant open-source projects include: https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipblaslt https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocblas, * Planning, designing, and refactoring existing codebases to improve maintainability and extensibility across multiple target hardware configurations * Developing new software designs to integrate a variety of code optimization patterns in a clear modular fashion in code generators * Identify and help resolve functional and performance issues by working closely with libraries development teams and other internal engineering teams * Participate in enhancing code integration process to verify conformance of new code submissions to the improved practices and designs * Apply a data minded approach to target optimization efforts * Stay informed of software and hardware trends and innovations, especially pertaining to algorithms and architecture * Design and develop new groundbreaking AMD technologies ## Related Videos - [Coffee with Developers - Stephen Jones - NVIDIA](https://www.wearedevelopers.com/videos/1303-coffee-with-developers-stephen-jones-nvidia) - [Accelerating Python on GPUs](https://www.wearedevelopers.com/videos/859-accelerating-python-on-gpus) - [ Secure Code Superstars: Empowering Developers and Surpassing Security Challenges Together](https://www.wearedevelopers.com/videos/422-secure-code-superstars-empowering-developers-and-surpassing-security-challenges-together) - [CUDA Python: GPU programming for the modern developer](https://www.wearedevelopers.com/videos/100221-cuda-python-gpu-programming-for-the-modern-developer) - [The weekly developer show: Boosting Python with CUDA, CSS Updates & Navigating New Tech Stacks](https://www.wearedevelopers.com/videos/1293-the-weekly-developer-show-boosting-python-with-cuda-css-updates-navigating-new-tech-stacks) - [A Deep Dive on How To Leverage the NVIDIA GB200 for Ultra-Fast Training and Inference on Kubernetes](https://www.wearedevelopers.com/videos/1625-a-deep-dive-on-how-to-leverage-the-nvidia-gb200-for-ultra-fast-training-and-inference-on-kubernetes) ## Related Articles - [How software is steering vehicle technology](https://www.wearedevelopers.com/magazine/515-how-software-is-steering-vehicle-technology) - [Best Countries for Software Engineers](https://www.wearedevelopers.com/magazine/267-best-countries-for-software-engineers) - [What’s the latest in NVIDIA CUDA Python](https://www.wearedevelopers.com/magazine/568-what-s-the-latest-in-nvidia-cuda-python) - [7 Important Tips That Every Software Developer Should Know](https://www.wearedevelopers.com/magazine/101-7-important-tips-that-every-software-developer-should-know) - [How Much FAANG Companies Actually Pay Software Engineers in 2025](https://www.wearedevelopers.com/magazine/230-how-much-faang-companies-actually-pay-software-engineers-in-2025) - [Highest Paying Tech Companies for Developers](https://www.wearedevelopers.com/magazine/220-highest-paying-tech-companies-for-developers)