18 hours ago
Santa Clara, CA, USASenior
Base Salary
$204k - $306k/yr
Responsibilities
- Profile and optimize large-scale AI workloads, including transformers, multimodal models, diffusion models, and recommender systems, across multi-node, multi-GPU systems.
- Perform GPU kernel-level analysis of compute pipelines, memory hierarchy, instruction execution, synchronization, and data movement.
- Use performance counters, thread traces, profilers, ISA/assembly analysis, and targeted microbenchmarks to root-cause bottlenecks and deliver low-level kernel optimizations.
- Collaborate with kernel, compiler, runtime, framework, distributed systems, and GPU architecture teams to improve kernel performance, scheduling, memory utilization, and system efficiency.
- Develop and maintain benchmarks, microbenchmarks, traces, and reproducer kernels for foundation model and broader AI workloads.
- Provide kernel- and microarchitecture-level performance insights to AMD Instinct GPU architecture teams and inform hardware/software co-design decisions.
- Present findings to cross-functional teams and leadership and help shape software and hardware roadmaps.
Requirements
- MS or PhD in Computer Science, Computer Engineering, or a related technical field.
- Strong hands-on experience with GPU kernel-level performance analysis and low-level optimization using CUDA, HIP/ROCm, or equivalent technologies.
- Deep understanding of GPU microarchitecture, including execution pipelines, SIMD/SIMT scheduling, registers, memory hierarchy, caches, and interconnects.
- Experience using performance counters, thread traces, profilers, and ISA/assembly analysis to identify GPU kernel performance bottlenecks.
- Hands-on experience optimizing performance-critical GPU kernels and developing targeted microbenchmarks or reproducer kernels.
- Proficiency in C++ and GPU kernel programming, with Python experience for performance analysis and automation.
- Advanced Linux OS, container technologies such as Docker, and Git/GitHub skills.
- Familiarity with AI workloads, AI frameworks, distributed computing, and communication libraries such as PyTorch, JAX, Megatron-LM, NCCL/RCCL, and MPI.
- Preferred qualifications include a strong record of GPU kernel performance improvements and experience collaborating across kernel, compiler/runtime, framework, distributed systems, and GPU architecture teams.
Benefits
- Benefits are offered, with details provided through AMD benefits at a glance.
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.