多模态推理infra实习生
北京
校招
实习
技术 - 算法
2027校园招聘
职位 ID：A21072
职位描述
关于我们 我们是一支专注于端侧多模态大模型推理的团队，致力于让大模型在手机、PC 等设备上实现实时的多模态交互。团队维护自研的开源推理引擎，并持续参与开源社区建设。 职位描述 1、负责推理引擎的核心设计与开发，包括计算图优化、算子与 Kernel 实现、内存与 KV Cache 管理、多流调度； 2、负责实时流式推理链路的设计与优化，覆盖多模态流式编码、多流同步、多模块并行流水线，以及语音链路的 TTS 与声码器，持续优化首包延迟与实时率； 3、负责端侧推理的落地与加速，包括主流 GPU / NPU 后端适配、模型格式转换与量化压缩、内存与显存优化； 4、参与开源项目建设与社区协作，并与训练团队配合打通训练到推理的全链路，跟踪并落地前沿推理优化技术。
职位要求
1、熟悉大模型架构与推理原理，理解计算图、算子、内存布局、KV Cache 等底层细节； 2、熟悉 C++ 和 Python，有扎实的工程基础与良好的代码能力； 3、有主流推理框架 / 引擎的源码级二次开发经验，如 vLLM、SGLang、TensorRT-LLM、llama.cpp 等；端侧推理引擎经验优先； 4、至少熟悉一种 GPU / 加速后端编程：CUDA、Metal、CANN / HIP / SYCL 等。 加分项 1、有全模态 / 多模态大模型推理优化或引擎开发经验； 2、有流式 / 低延迟系统经验（多线程异步流水线、并发与调度、性能剖析），或有语音链路经验（TTS、声码器、流式语音合成、voice cloning）； 3、有端侧 / 移动端部署与优化经验（iOS / Android、交叉编译、GPU / NPU 适配），或有大模型推理性能优化经验（量化、内存优化、并行与调度）； 4、有知名开源项目的核心贡献或 maintainer 经历。
投递
ModelBest established in August 2022, is an Artificial Intelligence technology company headquartered in Beijing, China. The company is deeply rooted in the field of general AI, with a focus on the innovation and application transformation of large-scale models. ModelBest boasts a prestigious founding R&D team from the Tsinghua in the AI field. Leveraging numerous cutting-edge technologies in natural language processing, the company is currently constructing a large-scale pre-trained model library and corresponding tools, aiming to standardize the technology and applications of large models.
Based on the capabilities of the CPM series of large models, ModelBest has successfully facilitated the intelligent upgrade and efficiency enhancement of various industries. Moreover, the company has released a multi-modal dialog assistant with hundreds of billions of parameters, “Luca", to the public. Adhering to the core philosophy of "intelligence encompassing all", we look forward to exploring and expanding unknown possibilities with global partners, aiming to ensure AI technology serves humanity for a better life in a safe and inclusive manner, laying a solid foundation for the advent of the AGI world.
OpenBMB (Open Lab for Big Model Base，https://github.com/OpenBMB), founded by ModelBest Inc & TsinghuaNLP, aims to build foundation models and systems towards AGI.
