# 顶尖应届-具身大模型算法研究员-具身模型与应用部

External opening: you cannot apply through AI Native Match; apply on the official site.

Apply through the official channel. The full external receipt stays in your workspace. When signed in, three minimal event types explicitly recorded through the CLI are reported by default: selection, self-reported application and channel observation. Browsing or saving a role does not report an event; external applications do not appear under My applications.

- Company: 小米 (Stage unknown)
- Locations: 北京
- Role: Algorithm
- Apply on the official site: https://xiaomi.jobs.f.mioffice.cn/toptalent/position/7646711224218372388/detail

## Role description from source

1、设计并实现 VLA / Embodied VLM / World Model 的训练目标、分布式训练方案与数据 recipe，融合互联网图文、视频、3D / 仿真、真机轨迹等多源数据；
2、设计并实现融合视频生成与动作控制的多模态大模型架构，探索大规模数据缩放定律，利用海量互联网视频数据及机器人采集数据，提升模型在零样本场景下的任务泛化能力；
3、研发基于 VLM 的端到端导航与具身 Agent 算法；
4、构建具身大模型的评测基准与真机闭环验证 pipeline；
5、跟踪并复现 SOTA 工作，与训练 / 推理 / 数据 / 硬件团队协同迭代
任职要求
1、CV / ML / 机器人 / AI 相关方向博士，或同等研究能力的硕士；
2、在 VLM / 多模态大模型 / 视频理解 / 3D 视觉 / VLN / Embodied Agent / RL / 视频生成 / 世界模型 任一方向有扎实基础；
3、至少在 CVPR / ICCV / ECCV / NeurIPS / ICML / ICLR / ACL / RSS / CoRL / ICRA / IROS 等顶会以一作发表过相关工作；
4、熟练 PyTorch，熟悉 Transformer、Diffusion、CLIP / SigLIP / Qwen-VL 等主流架构，具备分布式训练 / 大规模数据处理经验者优先；
5、系统思维强，对"什么是真正重要的具身问题"有自己的判断，能独立 own 一个研究方向，具备极强的自驱力，能够从 0 到 1 推动前沿技术在真实物理世界落地。
接口顶部原始条件（未做资格推断）
{"city_list": [{"code": "CT_11", "en_name": "Beijing", "i18n_name": "北京", "location_type": 3, "mdm_code": "MDCY00000001", "name": "北京", "node_status": 1, "py_name": "beijing"}], "job_post_info": {"HighlightList": [], "JobChannelPublishList": [], "address_list": [], "city_list": [], "correlation_job_list": [], "job_level_id_list": [], "job_post_object_value_map": {}, "job_post_process_time_list": [], "recruitment_type": {"active_status": 1, "children": [], "depth": 2, "en_name": "Regular", "i18n_name": "正式", "id": "201", "name": "正式", "parent": {"active_status": 1, "children": [], "depth": 1, "en_name": "Campus", "i18n_name": "校招", "id": "2", "name": "校招", "selectability": 1}, "selectability": 1}, "storefront_list": [], "tag_list": [], "target_major_list": []}, "process_type": 2, "project_type": 2, "recruit_type": {"active_status": 1, "children": [], "depth": 2, "en_name": "Regular", "i18n_name": "正式", "id": "201", "name": "正式", "parent": {"active_status": 1, "children": [], "depth": 1, "en_name": "Campus", "i18n_name": "校招", "id": "2", "name": "校招", "selectability": 1}, "selectability": 1}}

---
opening_id: b999d334-40e8-47a8-a15e-d84f267b0066

`anm openings save --id b999d334-40e8-47a8-a15e-d84f267b0066`