具身大模型部署与优化实习生 深圳 实习 互联网 / 电子 / 网游 职位描述 负责将大语言模型、多模态模型和具身智能模型高效部署到机器人端侧芯片和云端，实现低延迟实时推理。1、负责VLA（操作模型）等大模型在自研芯片上的端侧部署，完成模型量化（INT8/INT4/FP8）、图优化和推理加速；2、设计和优化模型推理服务（基于 vLLM/TensorRT-LLM），支撑 VLA 推理的低延迟需求；3、建立模型部署的标准化流程：模型转换→量化→性能基准测试→端侧验证→上线发布；4、模型优化，参与大模型的量化部署工作，探索模型在嵌入式端侧的高效运行；5、与算法团队协作，从模型设计阶段介入，提供部署可行性评估和性能预估。6、实验验证： 协助将算法部署至真实人形机器人平台，进行效果调试与性能评估。 职位要求 1、计算机、人工智能、自动化、机器人等相关专业在读硕士、博士、优秀本科生；2、 具备扎实的深度学习基础，熟悉 Transformer 架构，对 VLA 等主流模型有深入理解；3、熟悉 C++/Python，具备良好的代码风格和算法实现能力；4、有以下至少一项经验：-模型量化（PTQ/QAT/混合精度）与精度-速度 trade-off 调优；-CUDA 编程与 GPU kernel 优化；-嵌入式 NPU 部署（高通/联发科/NVIDIA Orin）；-熟悉至少一种推理框架：TensorRT / ONNX Runtime / vLLM /
Are you passionate about shaping the future of data center CPU platforms? NVIDIA is looking for a Solutions Architect experienced in Arm-based server CPUs to join our dynamic team in Shenzhen or Beijing, China. Act as
As a Senior CPU Expert focusing on Cloud Service Providers (CSPs) in China, you will be a core technical pillar in NVIDIA’s CSP team, responsible for driving CPU-related technical strategy, solution optimization, and customer engagement. You
Company Description WD is building the infrastructure behind the AI-driven data economy. As AI scales, so does data. Every interaction, every model, every system generates data that must be stored, managed, and made accessible over