AI Models GPU Deployment Software Engineer
职位介绍
You will enable and optimize key AI models (LLMs, Vision, MultiModal) on AMD GPUs.
Tuning and accelerating AI frameworks (PyTorch, TensorFlow) in upstream repositories.
Collaborate with internal GPU library teams to analyze training and inference pipelines.
Work with open-source framework maintainers to integrate changes upstream.
Optimize GPU kernels and AI operators (GEMM, Attention) for scale-up (multi-GPU) and scale-out (multi-node) deployments.
Apply software engineering best practices—debugging, testing, and performance analysis—to deliver robust solutions.
Tuning and accelerating AI frameworks (PyTorch, TensorFlow) in upstream repositories.
Collaborate with internal GPU library teams to analyze training and inference pipelines.
Work with open-source framework maintainers to integrate changes upstream.
Optimize GPU kernels and AI operators (GEMM, Attention) for scale-up (multi-GPU) and scale-out (multi-node) deployments.
Apply software engineering best practices—debugging, testing, and performance analysis—to deliver robust solutions.
查看完整职位
工作职责、任职要求、技能与福利 — 免费创建账号即可查看。
已有账户？ 登录
相似职位
其他可能适合您的职位。