深度学习模型量化与压缩_XC
Bosch · Shanghai, Shanghai, China
Apply on Bosch’s siteAsk about this jobApply opens the employer’s own application. Nothing is sent from here.
What the posting says
Each fact carries its state:Statedfound in the postingConflictstwo statements disagree, both quotedNot mentionedthe posting does not say
- Employment typeStated
- Full time
Not mentioned in this posting
“Not mentioned” means the posting does not say. It is not a no. You could ask the recruiter.
- PayNot mentioned
- The posting does not say
- Work arrangementNot mentioned
- The posting does not say
- ShiftNot mentioned
- The posting does not say
- ExperienceNot mentioned
- The posting does not say
- EducationNot mentioned
- The posting does not say
- Visa sponsorshipNot mentioned
- The posting does not say
Requirements, each with its sentence from the posting
These are the employer’s words. The index does not judge whether you meet them.
- No requirement has been itemised for this posting yet. The employer’s words are in the full posting below.
Read the full posting as the employer wrote it
Company Description
Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology - with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch.
Job Description
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。
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
The posting text is reproduced as the employer wrote it; the index adds nothing to it.