Machine Learning Performance Engineer, Annapurna Labs
职位介绍
Design, implement, and maintain software solutions to maximize end-to-end ML performance across the full software stack.
Analyze and optimize high-performance ML workloads running on accelerator hardware, focusing on instruction scheduling, memory hierarchy, and parallelism.
Develop and optimize high-performance kernels for core ML operations used by popular frameworks.
Enhance the Neuron SDK and related tooling to improve developer experience and system capabilities.
Collaborate across Compiler, Frameworks, and Hardware teams to diagnose bottlenecks and drive performance improvements.
Work in a startup-like environment, delivering high-impact solutions and influencing technical decisions with measurable impact.
Analyze and optimize high-performance ML workloads running on accelerator hardware, focusing on instruction scheduling, memory hierarchy, and parallelism.
Develop and optimize high-performance kernels for core ML operations used by popular frameworks.
Enhance the Neuron SDK and related tooling to improve developer experience and system capabilities.
Collaborate across Compiler, Frameworks, and Hardware teams to diagnose bottlenecks and drive performance improvements.
Work in a startup-like environment, delivering high-impact solutions and influencing technical decisions with measurable impact.
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。