AI Models GPU deployment software Engineer
职位介绍
Develop and optimize AI models (LLMs, Vision, MultiModal) on GPUs to boost training and inference performance.
Enhance AI frameworks like PyTorch and TensorFlow in upstream repositories and collaborate with framework maintainers.
Optimize GPU kernels and AI operators (GEMM, Attention) and drive performance on scale-up (multi-GPU) and scale-out (multi-node) systems.
Work in a Linux environment using C++ and Python, applying software engineering best practices, debugging, testing, and performance analysis.
Partner with internal GPU library teams and contribute to open-source initiatives to ensure upstream integration.
Combine independent ownership with collaborative teamwork to deliver robust, scalable, and maintainable code.
Enhance AI frameworks like PyTorch and TensorFlow in upstream repositories and collaborate with framework maintainers.
Optimize GPU kernels and AI operators (GEMM, Attention) and drive performance on scale-up (multi-GPU) and scale-out (multi-node) systems.
Work in a Linux environment using C++ and Python, applying software engineering best practices, debugging, testing, and performance analysis.
Partner with internal GPU library teams and contribute to open-source initiatives to ensure upstream integration.
Combine independent ownership with collaborative teamwork to deliver robust, scalable, and maintainable code.
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。
或
已有账户？
登录相似职位
其他可能适合您的职位。