3 days ago
San Jose, CA, USAStaff+
Base Salary
$240k - $360k/yr
Responsibilities
- Lead performance optimization of large-scale AI training, reinforcement learning, and inference workloads on AMD GPU platforms.
- Identify and eliminate compute, memory, and communication bottlenecks across single-node and multi-node systems.
- Drive cross-stack optimization spanning kernels, compilers, runtimes, communication libraries, and ML frameworks.
- Develop and apply profiling, benchmarking, and performance-modeling methodologies.
- Collaborate with hardware, compiler, and framework teams to influence GPU architecture and software-stack design.
- Lead or contribute to open-source efforts that improve performance on AMD platforms.
- Track advancements in large-scale systems and performance-optimization techniques.
Requirements
- Master’s degree or PhD in computer science, computer engineering, or a related field, or equivalent experience.
- Deep expertise in GPU architecture, compute units, memory hierarchies, interconnects, and GPU performance characteristics.
- Experience with GPU performance profiling tools, including ROCm tools, Nsight-like systems, or custom profilers.
- Proven experience optimizing large-scale distributed training workloads across thousands of GPUs.
- Experience with Megatron-LM, Torchtitan, vLLM, Sglang, or equivalent frameworks.
- Strong understanding of communication libraries, collective operations, and overlapping computation with communication.
- Proficiency in Python and at least one systems language such as C++, CUDA, or HIP, including debugging and low-level optimization.
- Experience with compiler stacks, kernel optimization, or graph-level optimization is preferred.
- Demonstrated technical leadership and ability to influence cross-functional teams.
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.