{"code":0,"data":{"job_post_detail":{"id":"7468481103957344364","title":"大模型技术专家（Agent方向）","description":"探索大模型智能体研究的前沿技术，构建具备持续学习能力的通用 Agent，包括但不限于：\n1、Agentic RL。面向长时序任务的强化学习；Agent 在交互环境中的探索与策略优化；多目标、多约束条件下大模型Agent的决策稳定性与泛化性；Test-time的数据高效Agentic RL；Agent reward model的系统性学习问题；大模型智能体的MARL。\n2、Agentic Memory。短期 / 中期 / 长期记忆架构设计；可演化、可压缩、可检索的Memory 系统；经验、技能、失败案例的结构化沉淀；Memory 与 Planning / RL / Tool 之间的协同机制。\n3、Agent Workflow。Task Decomposition / Planning / Re-planning；多 Agent 协作与角色分工；反思、自我修正、策略升级；工具集和技能库自演进；自适应和可学习的Agent 工作流。\n4、Agent Application。GUI Agent：跨应用、多模态界面下的操作与理解；OS Agent：文件系统、进程、命令、自动化工作流；Deep Research Agent：复杂研究任务、信息整合、假设验证；通用 Agent ：跨时间跨任务跨领域的自主学习Agent。\n\n\n","requirement":"1. 计算机相关方向硕士或博士；\n2. 有大模型智能体相关研究和项目经历，发表过相关方向的顶会论文，或者参与过有影响力的开源项目;\n3. 具有优秀的解决复杂问题和多人协作沟通的能力，能够独立思考并开展工作，具有强烈的好奇心和责任心。","recruit_type":{"id":"101","name":"全职","en_name":"Full-time","i18n_name":"全职","depth":2,"parent":{"id":"1","name":"社招","en_name":"Experienced","i18n_name":"社招","depth":1,"children":[],"active_status":1,"selectability":1},"children":[],"active_status":1,"selectability":1},"publish_time":1738892376775,"channel_online_status":1,"code":"A55228","job_id":"7468481103957278828","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":"101","name":"全职","en_name":"Full-time","i18n_name":"全职","depth":2,"parent":{"id":"1","name":"社招","en_name":"Experienced","i18n_name":"社招","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":1},"recommend_job_post_List":[]},"message":"ok","error":null}