2 months ago
Markham, CanadaSenior
Responsibilities
- Enable and optimize large-scale LLM, VLM, and MoE training on AMD Instinct GPU clusters.
- Build training infrastructure for orchestration, distributed checkpointing, data loading, storage optimization, monitoring, alerting, and compliance.
- Debug distributed training issues and optimize RCCL collective communication across multi-node GPU topologies.
- Develop validation and testing infrastructure using proxy workloads, synthetic benchmarks, and configurable workload generators.
- Write and optimize GPU kernels for GEMM, attention, quantized matrix multiplication, and GPTQ/AWQ workloads.
- Enable frontier models on new AMD GPU silicon and optimize vLLM, SGLang, and TorchServe for production inference.
- Build quantization pipelines and novel inference acceleration and scheduling approaches.
- Collaborate with silicon architecture and pre-silicon teams on software-stack integration and GPU validation.
- Build observability and automated analysis tooling for large-scale GPU clusters and contribute to the ROCm ecosystem.
Requirements
- Production experience shipping AI/ML infrastructure spanning both training and inference.
- Hands-on experience enabling frontier models on real hardware, preferably AMD Instinct GPUs.
- Experience with large-scale distributed GPU infrastructure, anomaly detection, log analysis, or observability systems.
- Familiarity with AMD Instinct MI-series architectures and the RCCL communication library.
- Contributions to open-source AI frameworks such as PyTorch, vLLM, SGLang, DeepSpeed, or Megatron-LM.
- Experience designing validation frameworks, proxy benchmarks, or synthetic workload suites for GPU infrastructure.
- Experience with pre-silicon software validation or hardware-software co-verification workflows is preferred.
- Publications or patents in HPC, ML systems, or GPU kernel optimization are preferred.
- Bachelor's, master's, or Ph.D. degree in computer/software engineering, computer science, or a related technical discipline.
Benefits
- Role location: Markham, Canada.
- AMD benefits are referenced through its benefits-at-a-glance information.
Tech Stack
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.