- San Jose, California, United States
- On-site
- Full-time · Principal
We are seeking a GPU performance engineering lead to join our team. This role focuses on maximizing performance and efficiency of large-scale AI training/RL/inference workloads on AMD GPU platforms. You will drive innovations across the full software-hardware stack, optimizing at scale and pushing the limits of system throughput, scalability, and utilization for generative AI workloads.
Responsibilities
- Lead performance optimization of large-scale AI training/RL/inference workloads on AMD GPU platforms across single-node and multi-node environments
- Identify and eliminate system bottlenecks across compute, memory, and communication
- Drive cross-stack optimizations spanning kernels, compilers, runtimes, communication libraries, and ML frameworks
- Develop and apply advanced profiling, benchmarking, and performance modeling methodologies
- Collaborate with hardware, compiler, and framework teams to influence next-generation GPU architecture and software stack design
Requirements
- Masters or PhD or equivalent experience in Computer Science, Computer Engineering, or related field
- Nice to have: Megatron-LM
- Nice to have: Torchtitan
- Nice to have: vLLM
- Nice to have: Sglang