15 hours ago
Belgrade, SerbiaSenior
Responsibilities
- Design and develop high-performance GPU kernels for machine learning and convolution workloads using HIP.
- Collaborate with GPU architects to evaluate and leverage emerging hardware features.
- Analyze, profile, and optimize GPU kernel performance.
- Create technical documentation, share best practices, and support adoption of new ROCm capabilities.
- Partner with engineers, researchers, customers, and ecosystem partners to improve ROCm applications, libraries, tools, and hardware.
Requirements
- Bachelor’s degree in computer science, computer engineering, or a related technical field.
- Significant experience in GPU software development, machine learning, HPC, or a related domain.
- Experience with GPU architecture, performance analysis, algorithm development, and machine learning workloads.
- Hands-on experience developing and optimizing GPU software using HIP, CUDA, or similar technologies.
- Understanding of GPU runtimes, compilers, machine learning frameworks, HPC libraries, and performance optimization techniques.
- Knowledge of software engineering practices including testing, profiling, debugging, version control, and documentation.
- Strong communication and collaboration skills across multidisciplinary teams.
Benefits
- Hybrid work arrangement with up to three days per week in the office in Belgrade, Novi Sad, or Niš.
- AMD benefits are offered, as described in AMD’s benefits overview.
Categories
About AMD
AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.