BBYR Achieve
返回信息流
这是一条镜像帖。来源:北邮人论坛 / job-info / #971355同步于 2025/1/20
JobInfo机器人发帖

高通中国端侧模型压缩部署转正实习/正式offer【2025年毕业】

SeZZX
2025/1/20镜像同步0 回复
端侧AI模型压缩和部署优化,及相关AI研发工作,base北京东城,面向2025毕业的硕博生,可实习转正或直接参加面试发offer,欢迎大家投递呀[ema0] 简历发送至ljiuyuan@qti.qualcomm.com,有其他问题也可直接私聊或发送到zipppxuan@gmail.com[ema23] 岗位职责 1. Development of end-2-end AI tools, models or software to run quantized neural network models on Qualcomm leading edge hardware with optimal resource 2. Design and develop end-to-end test strategies and frameworks for complex software systems 3. Create and maintain automated test suites using modern testing tools and frameworks 4. Development of debugging/profiling tools and Qualcomm SDK to rapid deployment quantized models on device 5. Participate in code reviews and contribute to improving test coverage 6. Collaborate with cross-functional teams to understand requirements and design test approaches 7. Analyze test results and provide detailed feedback to development team 8. Conduct experiments to reproduce and optimize accuracies and performance of models 9. Related papers reading and summarization and presentation. 岗位要求 1. Currently pursuing or recently completed a degree in Computer Science, Artificial Intelligence, EE, or a related field. 2. Experience in large language model (LLM), vision-language model (VLM), and large vision model (LVM), including diffusers, multi-modality, CNNs, RNN/LSTMs, Transformer, and others. 3. Experience in Model quantization and compression, deployment in smartphones or other edge devices. 4. Strong mathematical skills - good foundations of linear algebra, matrix, differential algebra, statistics. 加分项 1. Have strong skill in C++ and Python programming 2. Experience in machine learning/deep learning algorithms and architectures, including CNNs, RNN/LSTMs, Transformer, LVM, LLM 3. Hands-on experience with ML frameworks, such as TensorFlow, PyTorch and Onnx Runtime 4. Have knowledge in on-device AI models deployment is a plus 5. Have knowledge in llama.cpp or ExecuTorch is a plus 6. Have knowledge in Qualcomm SNPE/QNN SDK is a plus
订阅后,新回复会通过你的通知中心匿名送达。
0 条回复
暂无回复 · 你可以订阅本帖等待新回复。