{"code":0,"data":{"job_post_detail":{"id":"7646734068289521983","title":"顶尖实习-智能体研究员-MiMo","description":"我们是小米大模型团队的 Post-training Agent Group，专注于 AI Agent 的研究前沿，持续推动模型智能上限。\n我们致力于构建能够在开放环境中理解目标、自主规划并在长周期交互中保持稳定可靠的 Agent 系统。我们的目标，是将这些能力沉淀为模型内生、可泛化、可扩展的基础能力。\n团队拥有充足的计算资源，并能够直接连接大规模真实应用场景，让研究想法在前沿模型、真实任务和用户反馈中得到快速验证。\n研究方向\n1、构建覆盖 Coding、Visual、General Agent 以及长程任务场景的评测体系，系统刻画模型能力边界，并通过分析模型行为与失败模式，识别制约能力提升的关键瓶颈；\n2、构建大规模、高质量的数据合成与筛选流程，持续提升模型在代码生成、搜索和通用工具使用等方向的基础能力；\n3、研究 Agentic RL 算法，设计有效的奖励信号、grader 以及 credit assignment 机制解决长程交互、稀疏奖励 和 reward hacking 等问题；\n4、提升大规模 Agent 强化学习的稳定性、训练效率与可扩展性；\n5、通过大规模 Agent 强化学习提升 Agent 在未见任务、长程任务和开放环境中的泛化能力与可靠性；\n6、探索 self-improvement、持续学习，以及模型与 Agent Harness 的协同演进。","requirement":"1、硕博以上学历，计算机相关专业， 具有 LLM post-training、Agent、RL 或模型评测方面的实际研究或项目经验；\n2、出色的 Data Sense 与 Evaluation Sense，能够通过严谨的实验设计、分析和迭代持续提升模型能力；\n3、扎实的编程和工程能力，熟练使用 Python、PyTorch，能够将研究想法实现为可靠、可复现、可扩展的实验系统；\n4、优秀的 Research Taste 和 High Agency，认同第一性原理与长期主义。 在 NeurIPS、ICML、ICLR、ACL、EMNLP 等顶级 AI 会议或期刊发表过高质量研究\n5、在有影响力的开源项目中做出过重要贡献；\n6、在 IMO/CMO、IOI/NOI、ACM-ICPC 等高水平数学、信息学或程序设计竞赛中取得突出成绩","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":1780394110071,"channel_online_status":1,"code":"A76700","job_id":"7646734068289358143","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}