Refine Reset All
Sort by
Location
Job Type
Employer/Recruiter
Date Posted
Location
Job Type
Employer/Recruiter
All Filters

Equalization Jobs In China - 3 Job Positions Available

Top Cities:
1 – 3 of 3 jobs
轻舟智航 QCraft jobs

模型量化工程师 北京、苏州 社招 全职 互联网 / 电子 / 网游 职位描述 我们需要一位专注于模型量化落地的实干型工程师。你将核心负责解决模型在量产芯片上部署时的精度损失问题,保障算法模型在地平线、英伟达、高通等平台上的精度与性能平衡。岗位职责模型量化实施:负责自动驾驶模型(CNN/BEV/Transformer/E2E/VLA)在目标芯片上的INT8/INT16/FP16量化工作。掉点分析与优化:深入分析量化带来的精度损失,定位敏感层,通过权重校正、偏置校正、敏感度分析等手段恢复模型精度。QAT/PTQ落地:根据模型特性选择合适的量化算法和量化策略,搭建微调环境,执行量化感知训练以修复精度。工具链适配:使用各芯片厂商提供的量化工具(如AIMET, Horizon Pytorch Plugin等)进行模型转换与验证。精度验证:建立完善的量化精度评估体系,对比浮点模型与定点模型的输出差异,输出详细的量化分析报告。 职位要求 任职要求经验要求:计算机、自动化等相关专业本科及以上学历,2-4年深度学习模型优化或部署经验。理论知识:深入理解量化基本原理,熟悉常见量化优化算法。量化优化经验:具备丰富的量化掉点排查经验,能熟练使用特征图可视化、层间误差分析等方法定位精度瓶颈。掌握常见的精度恢复手段,如Bias Correction、Equalization、AdaRound等。QAT实战能力:熟悉PyTorch/TensorFlow的量化接口,有实际搭建QAT流程、配置伪量化节点、处理量化算子融合的经验。框架与工具:熟练使用PyTorch,了解ONNX中间表示;熟悉TensorRT、TFLite或TVM中至少一种推理框架的量化流程。芯片适配:了解地平线、高通或英伟达芯片架构者优先,有复杂模型(异构、多任务、上万节点)量化掉点问题解决的经验者优先。加分项对端到端和VLA模型的量化难点有研究或实践经验。熟悉混合精度量化策略,能根据硬件特性自动搜索最优量化位宽。 投递...

轻舟智航 QCraft  12 days ago
Apple jobs

SummaryPeople here at Apple don’t just build products – we build the kind of wonder that has revolutionized entire industries. It’s the diversity of those people and their ideas that encourages the innovation that runs through

Apple  6 days ago
Apple jobs

SummaryPeople here at Apple don’t just build products – we build the kind of wonder that has revolutionized entire industries. It’s the diversity of those people and their ideas that encourages the innovation that runs through

Apple  6 days ago

Subscribe for job alerts and resources to make your job search easier!

Confirmation email sent to

Check your email and click on the link to start receiving your job alerts

Receive the latest job openings for:

equalization

Confirmation email sent to

Check your email and click on the link to start receiving your job alerts

All Filters Apply
Sort by
Location
Job Type
Employer/Recruiter