Xiaomi Technology

MiMo算法研究员-后训练

Xiaomi Technology  •  Onsite  •  9 days ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

MiMo算法研究员-后训练北京社招全职职位 ID:A06427职位描述 我们是小米MiMo团队的 Post-train 组,专注模型对齐、可扩展强化学习、AI Agent 等前沿方向,致力于产出世界级研究成果与模型。
我们拥有充足算力与真实应用场景,汇聚了一批对 AGI 怀有长期信念、追求技术深度的研究者与工程师。在开放、专注的氛围中,我们鼓励从第一性原理出发,共同探索通往更高级人工智能的路径。
主要研究方向
1. AI 智能体 (AI Agent)
- Agent 基础能力:研发大规模、高质量的 Agent 数据合成管线,提升模型在 Code、Search 及 General Tool Use 使用等场景下的能力。
- 高级 Agent 系统:探索多智能体协作、长时记忆系统及交互环境的构建,提升模型解决复杂任务能力。
2. 大语言模型推理 (LLM Reasoning)
- 强化学习与推理:探索高效、稳定的强化学习算法。
- 推理能力提升:增强模型在数学、代码与逻辑等复杂任务中的推理能力,提升模型的智能上限。
3. 可扩展对齐 (Scalable Alignment)
- 模型对齐与 RLHF:持续提升模型的指令遵循度、有用性与诚实性。
- AI 安全与价值观:为大模型构建可靠、可信的行为准则,提升 AI 安全性。职位要求我们对你的期待
- 拥有大语言模型 Post-train(如 SFT, RLHF, RLVR, Agent)相关的研究或项目实践经验。
- 具备扎实的 Data Sense 和 Evaluation Sense,能够以问题为导向,通过严谨的实验设计和数据分析驱动模型迭代。
- 具备出色的编程与工程能力,熟练掌握 PyTorch 等深度学习框架,并对 Verl、Megatron 等分布式训练方法有深入理解;熟悉 SGLang、vLLM 等高性能推理引擎。
加分项
- 作为主要贡献者主导或参与过有影响力的开源项目。
- 在 NeurIPS、ICML、ICLR、ACL、EMNLP 等人工智能顶级会议或学术期刊上发表过高质量论文。
- 在 IMO/CMO、IOI/NOI、ACM-ICPC 等国内外知名竞赛中取得过优异成绩。 投递
Xiaomi Technology

About Xiaomi Technology

Xiaomi Corporation was founded in April 2010 and listed on the Main Board of the Hong Kong Stock Exchange on July 9, 2018 (1810.HK). Xiaomi is a consumer electronics and smart manufacturing company with smartphones and smart hardware connected by an IoT platform at its core.

Embracing our vision of “Make friends with users and be the coolest company in the users’ hearts”, Xiaomi continuously pursues innovations, high-quality user experience and operational efficiency. The company relentlessly builds amazing products with honest prices to let everyone in the world enjoy a better life through innovative technology.

Xiaomi is one of the world's leading smartphone companies. The company has also established the world’s leading consumer AIoT (AI+IoT) platform,reached 558 million smart devices connected to its platform (excluding smartphones,laptops and tablets) as of September 30 2022. Xiaomi products are present in more than 100 countries and regions around the world. In August 2022, Xiaomi was included in the Fortune Global 500 list for the fourth year in a row, ranking 266th. The company is the fastest-rising Chinese technology conglomerate during the four-year period.

Xiaomi is a constituent of the Hang Seng Index, Hang Seng China Enterprises Index, Hang Seng TECH Index and Hang Seng China 50 Index.

Industry
IT & Software
Company Size
10,000+ employees
Headquarters
Beijing, CN
Year Founded
2010
Social Media