Principal AI Inference Systems Engineer

What you'll do

• Lead technical initiatives and provide architectural guidance for AI/ML infrastructure.
• Optimize LLM training and inference on AMD GPUs to enhance system efficiency.
• Develop infrastructure supporting Large Language Models (LLMs) and Agentic AI systems.
• Design and optimize AI workloads on GPU clusters, including large-scale orchestration.
• Debug and resolve complex performance issues across GPU, network, and runtime layers.
• Drive technical excellence and foster innovation within the organization.

What we're looking for

• 5+ years of experience in AI/ML infrastructure and performance-critical software development.
• Expert proficiency in C/C++ and Python for AI/ML projects.
• Solid understanding of transformer architectures and distributed training frameworks like Megatron-LM, DeepSpeed, PyTorch Distributed.
• Proven experience optimizing LLM training and inference pipelines with parallelism techniques.
• Hands-on experience designing and scaling AI platforms using Kubernetes, Ray, or Kubeflow.
• Familiarity with GPU architecture and communication libraries for multi-GPU training optimization.
• Demonstrated technical ownership and strong problem-solving skills in delivering end-to-end AI/ML solutions.