{"code":0,"data":{"job_post_detail":{"id":"7647448226383874313","title":"顶尖应届-OS Agent算法研究员-软件","description":"1、研究与优化多层级渐进式路由架构，设计端侧轻量分级器，提升路由决策准确性与响应速度\n2、攻关端云并行协同调度，实现意图理解和执行竞速，设计渐进式结果融合与弱网降级策略\n探索Plan-Execute-Learn范式在端侧Agent中的应用，构建可自主规划、执行、纠错和学习的智能体闭环\n3、研究多智能体协同执行框架，支持复杂任务的并行分解与协作完成\n优化端侧工具调用链路，扩展工具生态，提升工具选择与参数填充的准确性\n4、发表AI顶会/顶刊论文（ACL、NeurIPS、ICML、AAAI等），申报发明专利","requirement":"1、博士及以上在读，人工智能、计算机科学、软件工程、系统工程等专业，有C++/Python开发经验；\n2、熟练掌握至少一种深度学习框架，如PyTorch等；\n3、对LLM Agent、工具调用、任务规划等方向有深入研究或工程经验者优先；\n4、对强化学习、多智能体系统、分布式调度有实际经验者优先；\n5、对端云协同系统架构、移动端优化有理解者优先；\n在AI相关顶级会议或刊物（如ICML、NeurIPS、AAAI、ACL、ICLR等）发表论文者优先。","recruit_type":{"id":"201","name":"正式","en_name":"Regular","i18n_name":"正式","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":1780560500482,"channel_online_status":1,"code":"A158341A","job_id":"7647448226383694089","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":"201","name":"正式","en_name":"Regular","i18n_name":"正式","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}