{"code":0,"data":{"job_post_detail":{"id":"7559917059506358579","title":"顶尖实习-大模型芯片协同设计研究员-MiMo","description":"当模型规模触顶硬件天花板，真正的突破来自从模型到芯片的协同设计（Co-design）——让模型结构天然适配硬件特性，让芯片架构为模型量身定制。这正是我们在做的事。你将深入 MiMo 大模型的核心，从模型架构到推理效率，再到与自研芯片团队的深度协作，打通从算法到硅片的全链路。\n你会做什么？\n1、模型架构设计：参与大模型核心架构的探索与迭代，设计兼顾建模能力与计算效率的架构（如高效 Attention 等）；\n2、模型高效推理：研究低比特量化、稀疏化、投机解码等技术，在精度与推理效率之间找到最优解；\n3、端到端性能优化：从算子、内存访问模式到系统级调度，推动软硬件协同的极致性能；\n4、芯片协同设计：基于对芯片计算特性（数据流、存储层次、互联带宽）的理解，将模型侧的洞察转化为芯片架构的设计指引，与自研芯片团队紧密合作。","requirement":"我们希望你是这样的人：\n1、对大模型架构有扎实理解；\n2、熟悉推理优化技术栈（量化/稀疏/投机解码/高效算子等）；\n3、对芯片/计算机体系结构有真实兴趣 。\n加分项：\n1、有大模型训练/微调经验；\n2、有 CUDA/Triton kernel 开发经验；\n3、在系统、体系结构或 ML 方向的顶会有论文发表。","recruit_type":{"id":"202","name":"实习","en_name":"Intern","i18n_name":"实习","depth":2,"parent":{"id":"2","name":"校招","en_name":"Campus","i18n_name":"校招","depth":1,"children":[],"active_status":1,"selectability":1},"children":[],"active_status":1,"selectability":1},"publish_time":1760180561366,"channel_online_status":1,"code":"A148943","job_id":"7559917059506243891","city_list":[{"code":"CT_11","name":"北京","en_name":"Beijing","location_type":3,"i18n_name":"北京","py_name":"beijing","mdm_code":"MDCY00000001","node_status":1}],"job_post_info":{"recruitment_type":{"id":"202","name":"实习","en_name":"Intern","i18n_name":"实习","depth":2,"parent":{"id":"2","name":"校招","en_name":"Campus","i18n_name":"校招","depth":1,"children":[],"active_status":1,"selectability":1},"children":[],"active_status":1,"selectability":1},"HighlightList":[],"JobChannelPublishList":[],"job_post_object_value_map":{},"address_list":[],"city_list":[],"correlation_job_list":[],"tag_list":[],"storefront_list":[],"target_major_list":[],"job_post_process_time_list":[],"job_level_id_list":[]},"city_info_list_for_delivery":[{"code":"CT_11","name":"北京","en_name":"Beijing","location_type":3,"i18n_name":"北京","py_name":"beijing","mdm_code":"MDCY00000001","node_status":1}],"tag_list":[],"storefront_mode":1,"storefront_list":[],"process_type":2},"recommend_job_post_List":[]},"message":"ok","error":null}