Principal Machine Learning Researcher, On-Device Optimization
职位介绍
As a Principal ML Researcher focused on on-device optimization, you will bridge advanced research and product-ready deployment for edge AI systems.
You will lead research and implementation of model compression techniques such as quantization, pruning, distillation, and low-rank factorization.
You will develop methods to run state-of-the-art transformer and vision models on-device under hardware constraints.
You will drive hardware-aware training strategies to optimize latency, throughput, and memory usage, and collaborate with software engineers to integrate models into applications.
You will evaluate frameworks and quantization strategies (e.g., AWQ, GPTQ, SmoothQuant) and benchmark performance.
The role requires a PhD with related experience, expertise in edge ML, and strong collaboration and communication skills.
You will lead research and implementation of model compression techniques such as quantization, pruning, distillation, and low-rank factorization.
You will develop methods to run state-of-the-art transformer and vision models on-device under hardware constraints.
You will drive hardware-aware training strategies to optimize latency, throughput, and memory usage, and collaborate with software engineers to integrate models into applications.
You will evaluate frameworks and quantization strategies (e.g., AWQ, GPTQ, SmoothQuant) and benchmark performance.
The role requires a PhD with related experience, expertise in edge ML, and strong collaboration and communication skills.
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。