# Agent研发工程师

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: Engineering
- Apply on the official site: https://xiaomi.jobs.f.mioffice.cn/index/position/7675561126432344339/detail

## Role description from source

1. 建设 Agent 评测与自动化测试体系，覆盖任务完成率、推理、工具调用、鲁棒性及端到端、Prompt、对抗测试，集成 CI/CD。
2. 负责 Agent 任务识别、意图拆解与异常治理，完善链路追踪、问题定位及故障恢复。
3. 推动大模型与多模态能力落地，完成能力评估、工具集成及效果优化，兼顾性能、成本与可维护性。
任职要求
1. 相关专业本科及以上学历，3 年以上 NLP/CV/多模态或大模型应用研发经验。
2. 熟悉深度学习、Transformer 及 PyTorch，理解大模型能力边界；有训练、微调经验者优先。
3. 熟悉 Agent 技术栈及 Prompt、RAG、Function Calling，有实际项目落地经验。
4. 熟练使用 Python，具备服务开发与测试能力，了解 vLLM、TGI 等推理框架。
5. 能结合日志、调用链路及评测数据定位问题，优化效果与稳定性；有自动化测试、CI/CD 或平台建设经验者优先。
6. 熟悉 AI Coding，能独立审查、验证生成代码，具备跨团队协作与交付能力。
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": "Full-time", "i18n_name": "全职", "id": "101", "name": "全职", "parent": {"active_status": 1, "children": [], "depth": 1, "en_name": "Experienced", "i18n_name": "社招", "id": "1", "name": "社招", "selectability": 1}, "selectability": 1}, "storefront_list": [], "tag_list": [], "target_major_list": []}, "process_type": 1, "project_type": 1, "recruit_type": {"active_status": 1, "children": [], "depth": 2, "en_name": "Full-time", "i18n_name": "全职", "id": "101", "name": "全职", "parent": {"active_status": 1, "children": [], "depth": 1, "en_name": "Experienced", "i18n_name": "社招", "id": "1", "name": "社招", "selectability": 1}, "selectability": 1}}

---
opening_id: dffd2814-bd5d-4282-8de1-99e53ca881e3

`anm openings save --id dffd2814-bd5d-4282-8de1-99e53ca881e3`