Job Role and Responsibility: AMD, Inc. is hiring Sr. Software Development Engineer to research, design, develop, and test high-performance collective communication libraries, GPU communication runtimes, and benchmarking tools for AI/HPC workloads on AMD Instinct GPUs and next-generation accelerator platforms. Design, develop, optimize, troubleshoot, and debug software that enables efficient multi-GPU and multi-node communication across AMD's ROCm software stack. Contribute to open-source libraries for GPU communication, including RCCL (ROCm Collective Communications Library) and benchmarking tools including TransferBench, to maximize bandwidth utilization and minimize latency across PCIe, Infinity Fabric (xGMI), and high-speed network interconnects (RDMA/RoCE/InfiniBand). Develop and tune collective algorithms (AllReduce, AllGather, ReduceScatter, Broadcast, AllToAll, etc.) for distributed training and inference frameworks such as PyTorch, JAX, Megatron-LM, DeepSpeed, and vLLM. Design micro-benchmarks and performance characterization tools to evaluate GPU-to-GPU, GPU-to-NIC, and host-to-device transfer performance, and use results to influence hardware/firmware/topology decisions for upcoming AMD Instinct (MI-series) products. Collaborate with hardware, firmware, driver, and AI framework teams to bring up and enable new silicon, validate interconnect performance, and resolve cross-stack functional and performance issues. Work on problems of complex scope where analysis of situations and performance data requires review of architectural, system-level, and network-level factors. Apply knowledge of GPU architecture, parallel computing, networking (RDMA, NCCL/RCCL protocols), and modern AI/HPC workloads to the design, development, performance tuning, and testing of AMD's communication software and platforms.
Multiple openings. Qualified applicants click
"APPLY NOW" button to apply online.
Travel required: NO
Qualifications: Degree requiredMaster's degree or foreign equivalent in Computer Science, Computer Engineering, Electrical Engineering, or related field.
Qualifications: Amount and type of experience required: NONE
Specific skills required: The following skills are required:Position requires experience in the following:
- Python, C, or C++;
- Developing benchmarks to test software performance;
- GPU software programming and development;
- Software debugging (macOS, Linux, or Unix);
- Data structures and multi-threading; and
- CUDA.
Experience may be gained through graduate-level coursework, research, or internship experience.
Benefits offered are described: AMD benefits at a glance.
