{"code":0,"data":{"job_post_detail":{"id":"7681240458697345307","title":"AI Agent研究员实习生-小爱","description":"1、探索下一代Harness实现与RSI范式，从第一性原理重新设计Agent Runtime: 包括但不限于上下文工程、长程任务、工具使用、记忆等，让系统自我修正、自我迭代。\n2、持续调研全球SOTA，追踪、拆解、复现全球最领先的 Harness 与智能体实现(前沿实验室产品、开源框架、顶会最新工作)，形成团队可复用的技术判断。\n3、从0到1构建关键模块，独立设计并落地 Harness 的核心组件，或为 RSI 搭建所需的评估体系、reward model、Environment Scaling等。\n4、Harness 与 LLM 的 co-design 和协同训练。 主导或参与面向 Harness 的模型选型、mid-training(继续预训练)与 post-training(SFT、RLHF / RLAIF / RLVR、蒸馏), 让模型和Harness作为一个系统共同优化。","requirement":"1、计算机 / AI 相关方向硕士及以上;\n2、在 ICLR/NeurIPS/ICML/COLM/ACL/EMNLP 等顶会有一作或核心作者论文者优先(智能体、LLM 训练与对齐、推理、强化学习、自我改进方向)。\n3、熟练 Python / PyTorch，理解大模型训练与推理全链路(分布式训练、数据管线、LLM infra)，能把想法在真实系统里跑通、测准、复现。\n4、熟练掌握vibe coding 并对AI使用有自己的独特理解。\n5、自驱力强，创新能力强，学习能力突出，能快速上手新技术领域。\n\n加分项（有任意一项即可）：\n1、主导或深度贡献过知名开源智能体 / LLM 框架。\n2、有端到端训练大模型的一线经验(预训练 / 中训 / 后训任一阶段)。\n3、RL / RLHF / RLVR 实战,或对齐、奖励建模、评测体系(eval harness)的积累。","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":1788428277437,"channel_online_status":0,"code":"A101301","job_id":"7681240458697165083","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}