
商汤AI算法部署工程师
社招全职5年以上算法研究类地点:北京状态:招聘
任职要求
工作职责: 1.负责端上(Linux/Android)平台的模型部署; 2.负责大模型在NPU/DSP/GPU/CPU开发与部署; 3.负责大模型在端侧(NV/MTK/Qualcomm等)的量化及推理性能优化; 4.负责大模型测试工具的开发; 任职要求: 1.本科及以上学历,计算机科学、电子工程或自动化等相关专业; 2.5年以上工作经验,3年以上的嵌入式开发工作经验, 3.熟悉计算机系统体…
登录查看完整任职要求
微信扫码,1秒登录
工作职责
工作职责: 1.负责端上(Linux/Android)平台的模型部署; 2.负责大模型在NPU/DSP/GPU/CPU开发与部署; 3.负责大模型在端侧(NV/MTK/Qualcomm等)的量化及推理性能优化; 4.负责大模型测试工具的开发; 任职要求: 1.本科及以上学历,计算机科学、电子工程或自动化等相关专业; 2.5年以上工作经验,3年以上的嵌入式开发工作经验, 3.熟悉计算机系统体系架构,软件性能优化加速; 4.至少熟悉一种主流推理框架,如VLLM、HuggingFace Transformers,TensorRT等 4.熟悉Al训练框架(TensorFlow、PyTorch、Caffe等)优先; 6.有NVIDIA、MediaTek、Qualcomm、地平线等平台部署经验者优先; 7.熟练掌握C/C++、Python、Git、CMake、Makefile等基本技能
包括英文材料
Linux+
https://ryanstutorials.net/linuxtutorial/
Ok, so you want to learn how to use the Bash command line interface (terminal) on Unix/Linux.
https://ubuntu.com/tutorials/command-line-for-beginners
The Linux command line is a text interface to your computer.
https://www.youtube.com/watch?v=6WatcfENsOU
In this Linux crash course, you will learn the fundamental skills and tools you need to become a proficient Linux system administrator.
https://www.youtube.com/watch?v=v392lEyM29A
Never fear the command line again, make it fear you.
https://www.youtube.com/watch?v=ZtqBQ68cfJc
Android+
https://roadmap.sh/android
Step by step guide to becoming an Android developer .
https://www.youtube.com/playlist?list=PLQkwcJG4YTCSVDhww92llY3CAnc_vUhsm
大模型+
https://www.youtube.com/watch?v=xZDB1naRUlk
You will build projects with LLMs that will enable you to create dynamic interfaces, interact with vast amounts of text data, and even empower LLMs with the capability to browse the internet for research papers.
https://www.youtube.com/watch?v=zjkBMFhNj_g
学历+
vLLM+
https://www.newline.co/@zaoyang/ultimate-guide-to-vllm--aad8b65d
vLLM is a framework designed to make large language models faster, more efficient, and better suited for production environments.
https://www.youtube.com/watch?v=Ju2FrqIrdx0
vLLM is a cutting-edge serving engine designed for large language models (LLMs), offering unparalleled performance and efficiency for AI-driven applications.
TensorRT+
https://docs.nvidia.com/deeplearning/tensorrt/latest/getting-started/quick-start-guide.html
This TensorRT Quick Start Guide is a starting point for developers who want to try out the TensorRT SDK; specifically, it demonstrates how to quickly construct an application to run inference on a TensorRT engine.
TensorFlow+
https://www.youtube.com/watch?v=tpCFfeUEGs8
Ready to learn the fundamentals of TensorFlow and deep learning with Python? Well, you’ve come to the right place.
https://www.youtube.com/watch?v=ZUKz4125WNI
This part continues right where part one left off so get that Google Colab window open and get ready to write plenty more TensorFlow code.
还有更多 •••
相关职位

社招后端开发
1. 负责智能车舱AI算法模型的量化部署、芯片适配与性能优化; 2. 参与AI模型算子开发、前处理、后处理及SDK底层代码工程化开发; 3. 参与座舱AI新功能研发,并在主流SoC平台实现量产落地,优化资源占用与推理性能;
更新于 2025-05-26重庆|上海

社招后端开发
1. 负责智能车舱AI算法模型的量化部署、芯片适配与性能优化; 2. 参与AI模型算子开发、前处理、后处理及SDK底层代码工程化开发; 3. 参与座舱AI新功能研发,并在主流SoC平台实现量产落地,优化资源占用与推理性能;
更新于 2025-04-10上海
校招
1. 音频算法优化:分析和优化现有的音频处理算法,以提高性能和效率; 将深度学习算法推理用C/C++实现。;对算法做定点化,以便更高效运行在嵌入式系统中; 完成AI算法在芯片上的部署,必要时需要考虑量化噪声等问题进行模型重新训练; 2. 系统集成:将音频/健康算法集成到嵌入式系统中,确保与其他系统组件的无缝协作;参与系统架构设计,确保音频处理模块的高效集成; 3. 代码开发和维护:编写高质量、可维护的代码,遵循最佳编程实践;进行代码审查,确保代码质量和性能; 4. 测试和验证:和测试工程师合作,验证算法的功能和性能;解决算法处理中的问题和故障,确保系统的稳定性和可靠性。
更新于 2025-09-05北京