感知模型剪枝量化工程师_XC
Bosch · Suzhou, Jiangsu, China
What the posting says
Each fact was read from this posting and checked:Statedin the posting, quotedConflictsposted two ways, both shownNot mentionedwe looked; it is not there
- Employment typeStated
- Full time
Not mentioned in this posting
We read the whole posting. These are not in it. Not a no: ask the recruiter, in your own words.
- 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 itemized for this posting yet. The employer’s words are in the full posting below.
Read the full posting as the employer wrote it
Job Description
1、负责感知模型剪枝量化方案设计（结构化/非结构化剪枝、稀疏化训练、PTQ/QAT）,评估不同剪枝粒度对精度与推理性能的影响，INT8/FP16量化、校准算法选型、敏感层分析与混合精度策略；
2、建立剪枝与量化联合优化的模型压缩流水线，支持感知模型在算力受限量产平台上的高效部署，平衡精度与延迟、吞吐、内存占用；
3、分析模型各模块的计算量与敏感度，制定分阶段压缩策略，保证压缩后模型精度与鲁棒性不显著退化以及算子兼容与位一致性等问题；
4、建立压缩前后模型的精度对齐与回归验证流程，输出压缩评估报告并推动模型迭代闭环；
Qualifications
任职要求：
1、计算机、电子、自动化、数学等相关专业本科及以上学历，2年以上相关工作经验；
2、扎实的深度学习基础，熟悉 CNN/Transformer 等感知模型架构，有目标检测、分割或 BEV 感知等模型的训练或调优经验；
3、熟悉 PyTorch 等深度学习框架，熟悉 DPX平台、TensorRT、ONNX Runtime 等推理引擎及常见压缩工具；
4、熟悉模型量化与剪枝原理，有 INT8 量化或剪枝部署落地经验；
5、具备良好的工程能力（Python/C++），熟悉模型导出转换、推理部署与性能分析流程；
6、有自动驾驶/ADAS 感知或嵌入式平台部署经验者优先；
加分项：
1、有结构化剪枝、稀疏化训练、知识蒸馏或低比特量化等模型压缩落地经验；
2、有 NPU/BPU/GPU/嵌入式平台性能优化经验；
3、有车载量产项目交付经验。
The posting text is reproduced as the employer wrote it; the index adds nothing to it.