logo of mi

小米Use Agent 实习生— 环境合成与RL训练方向-2027届

实习兼职地点:武汉状态:招聘

任职要求


1. 在读本科高年级、硕士或博士,计算机、人工智能、软件工程、自动化、电子信息、数学等相关专业优先;对 GUI Agent、Computer-Use Agent、多模态大模型强化学习、环境合成、自动化评测等方向有较强兴趣,愿意持续跟踪前沿论文和开源项目;
2. 具备优秀的编程和工程实现能力,熟练掌握 PythonC++,熟悉 PyTorch 等至少一种深度学习框架;具备良好的实验分析和文档表达能力,能够独立阅读论文、复现方法、分析实验结果并沉…
登录查看完整任职要求
微信扫码,1秒登录

工作职责


1. 跟踪和调研 GUI Agent、Computer-Use Agent、Mobile Agent、Web Agent 等方向的前沿技术,重点关注环境合成、任务生成、自动评测、轨迹数据构建、RL/RLVR 训练等相关方法和开源项目;
2. 参与 GUI Agent 任务环境合成与可验证评测体系建设,包括移动端 / Web / 桌面任务环境设计、模拟应用构建、任务模板设计、状态建模、mock backend、任务完成判定、verifier / reward 信号设计等;
3. 参与 GUI Agent 数据与 RL 训练闭环建设,包括任务生成、轨迹采集、数据筛选、失败案例分析、困难样本挖掘、rollout 数据分析、训练环境接入和策略效果评估,持续提升模型任务完成率、泛化性和执行效率。
包括英文材料
AI agent+
大模型+
强化学习+
Python+
C+++
PyTorch+
还有更多 •••
相关职位

logo of netease
实习网易游戏(雷火)

业务场景:在开放世界游戏环境中,开展游戏内容理解与动态解说,驱动智能体完成指定任务、实现自主探索,并支持多智能体复杂交互等前沿 AI 应用场景。 岗位职责 1、参与开放世界游戏场景下 Agent 相关功能的开发与迭代,包括对话交互、任务流程、工具调用等模块; 2、在现有框架基础上进行功能完善与效果优化,协助提升可用性、稳定性与一致性; 3、参与探索提升 Agent 表现的思路与方案,例如经验复用、反思/自我纠错、策略调整等方向; 4、协助设计与实现基础的 memory 机制(写入、检索、总结/压缩等),并通过实验观察其对任务表现的影响。

更新于 2026-01-16杭州
logo of ctrip
社招旅游业务业务拓展

Partnership Development: Identify, negotiate, and secure partnerships with MNOs and MVNOs globally. Maintain strong relationships to ensure long-term collaboration and mutual growth. Contract Negotiation: Lead negotiations for partnership agreements, ensuring alignment with company strategy and objectives. Manage the end-to-end process from initial contact to contract signing. Market Expansion: Develop and implement strategies to expand the availability and reach of travel essentials products, driving market share growth in key regions. Product Enhancement: Collaborate with partners to develop and launch new products or services that meet the needs of travelers. Provide market insights to optimize product offerings and enhance customer satisfaction. Cross-functional Collaboration: Work closely with internal departments such as marketing, operations, and customer service to ensure seamless integration and execution of different projects. Performance Monitoring: Regularly review and analyze partner performance metrics. Provide insights and recommendations to improve outcomes and maximize ROI. Market Research: Conduct ongoing research on industry trends, competitor activities, and technological advancements in the telecom sector. Use this information to inform strategy and drive innovation. Reporting: Prepare regular reports on business partnership activities, market trends, and performance metrics for senior management.

更新于 2025-06-19上海
logo of alibaba
社招运营-用户运营

1. Plan and execute various platform level promotions: include big promotion such as Black Friday or seasonal rebajas, to drive platform level uplift and make the sales reach to new height, and several monthly campaigns which serve different objectives: increase seasonal sub-categories, boost re-purchase rate, assist incubation, drive top brands or top assortment 2. Think from both seller and buyer points of view. 3. Leverage analytical data to point out the critical factors or measurable metrics to enhance promotion performance, improve SOP or raise new promotional initiatives. 4. Work with Product and User Experience Design team to identify improvement areas that can largely improve business results and better user experience.

更新于 2025-06-19马德里
logo of alibaba
社招5年以上LAZADA

We are seeking a dynamic Manager to drive the success of Lazada Sponsored Solutions across Southeast Asia, covering Thailand, Vietnam, Philippines, Indonesia, Singapore, and Malaysia. In this role, you will craft data-driven strategies, advise cross-border sellers, and lead go-to-market initiatives for new product solutions—all aimed at maximizing the impact of our digital advertising platform. The ideal candidate combines strong product management, data analytics, and B2B marketing skills with an in-depth understanding of platform-based and digital advertising business models. You will play a pivotal role in promoting the adoption of Lazada Sponsored Solutions and driving growth for our e-commerce ecosystem. If you are passionate about leveraging data and innovation to fuel e-commerce success, we invite you to join our team and make a significant impact in the region. Responsibilities: • Develop and execute B2B product strategies and marketing campaigns designed to boost seller engagement and success. • Craft compelling product positioning and narratives that resonate with our target customers and set our solutions apart in Southeast Asia. • Clearly articulate the unique value propositions of Lazada Sponsored Solutions to both internal and external stakeholders. • Lead the creation of engaging and informative marketing content across assigned product domains and projects. • Manage end-to-end product launches, ensuring consistent communication with all stakeholders and timely delivery of key deliverables. • Drive successful B2B marketing campaigns primarily through our owned channels. • Monitor key performance metrics and analyze data to uncover growth opportunities. • Conduct thorough market research to identify target seller segments, understand their needs, and analyze relevant product use cases. • Develop detailed seller personas to inform product positioning and messaging strategies. • Collaborate with the account management team, providing them with the insights and tools necessary to effectively promote Lazada Sponsored Solutions. • Oversee critical B2B marketing operations, including governance and traffic generation, to support overall campaign success.

更新于 2025-09-12杭州