深度学习模型量化与压缩_XC

Bosch · Shanghai, China · full-time · On site · May 07, 2026

Sign up to apply
Your first one is free
Posted May 07, 2026 · Read from Bosch
Why a CV for this job?

94% of employers say their filters drop qualified candidates whose CV does not match the ad's exact criteria (Harvard Business School, 2021).

  • They see what they asked for, first. Your experience that matches the ad leads, in the ad's own words, so someone skimming finds it in seconds.
  • It gets past the software. Many larger employers use software that ranks CVs by how closely they match the ad, often before anyone reads them.
  • In the language of the ad. An ad written in Spanish gets a CV in Spanish, even when yours is in Portuguese.
  • Your facts, nothing invented. Your own experience, reordered and reworded. What the ad wants and your CV does not show is listed for you to add, only if it is true. You check it before you send it.
See an example

Qualifications

  • 学历背景： 计算机科学、电气工程或相关领域的硕士及以上学位。
  • 工作经验： 至少5年深度学习领域的经验，尤其在模型量化与压缩方面。
  • 技术技能：熟练掌握 Python 和 C++。熟悉 PyTorch 和 TensorFlow 等深度学习框架。在后训练量化和量化感知训练技术方面有丰富实践经验。掌握剪枝、知识蒸馏和低秩分解等模型压缩技术。深刻理解嵌入式系统限制及GPU、NPU等硬件加速器的应用经验。
  • 领域知识：有自动驾驶行业经验者优先。熟悉ADAS系统和感知算法优先。
  • 加分项： 有使用 NVIDIA TensorRT、TVM 或 PyTorch FX 等优化工具的经验。了解实时系统与嵌入式软件开发。在地平线芯片或者高通芯片部署过模型

主要工作内容：

  • 模型量化与压缩：开发并实现前沿技术，对深度学习模型进行量化和压缩，以优化模型在嵌入式芯片上的性能。基于实验依据在模型精度、大小和推理速度之间做权衡，给出优化方向。在后训练量化（Post-training Quantization）、量化感知训练（Quantization-Aware Training）以及剪枝（Pruning）等领域有深入理解。
  • 嵌入式系统部署：调整并部署深度学习模型至嵌入式平台，确保硬件资源的高效利用。针对特定硬件加速器优化模型耗时。
  • 性能分析：对模型进行性能分析，识别瓶颈并实施策略，提升实时推理能力。使用工具和框架调试和优化嵌入式设备上的神经网络性能。
Employer
Bosch
Location
Shanghai, China · On site
Contract
full-time