# AI算法工程师-AICoding/Agents方向

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, 武汉
- Role: Algorithm
- Apply on the official site: https://xiaomi.jobs.f.mioffice.cn/campus/position/7671291137243629878/detail

## Role description from source

1、负责代码智能体（Coding Agent）系统全流程研发：数据构建（代码语料清洗、代码/对话/工具轨迹标注）、预训练/持续预训练、指令微调（SFT）与后训练（DPO/ORPO/RLHF/RLAIF），在 HumanEval、MBPP、SWE-bench、RepoBench 等基准及业务集上达成目标。
2、基于主流 Agents 框架（LangChain、AutoGen、Agno 等）搭建具备规划、工具调用、记忆与多步推理能力的多代理系统，落地代码生成、调试与单测生成、仓库级理解、自动修复、PR 评审与CI修复等核心场景。
3、以 MCP（Model Context Protocol）为核心构建工具生态：设计与实现 MCP servers/tools，标准化接入代码搜索、编译/运行、CI/CD、Issue/PR、知识库与内部服务；支持安全沙箱执行与资源隔离，提升可观测与可维护性。
4、设计并优化 ReAct/Plan-Act/Tree-of-Thought 等推理策略及函数调用，结合 RAG（向量/符号/结构化检索与代码图）实现大规模代码库检索增强，支持跨文件、跨仓库的复杂问题求解。
任职要求
1、计算机基础扎实，熟练使用 Python，至少掌握一门强类型语言（Go/Java/C++/Rust 优先）；熟悉 Git、Linux 与容器化开发。
2、熟悉主流 Agents 框架与范式：有 LangGraph/LangChain/AutoGen/LlamaIndex/CrewAI 之一的实战经验；理解 MCP 协议并能实现自定义 MCP 工具；熟悉 ReAct、RAG、Function Calling、Planner/Memory 等方法并能落地。
3、了解大模型训练与推理：可使用 PyTorch/DeepSpeed/Lightning/Colossal-AI 等完成 SFT/LoRA/QLoRA；理解后训练与对齐方法；熟悉 Transformers/vLLM/TGI 等高效推理与服务化。
4、具备良好的实验设计与问题定位能力，能分析 Agent 轨迹、工具失败率、检索召回与推理路径，提出可量化改进方案。
5、良好的沟通与团队协作能力，关注用户体验，能与产品/前端/平台协同推进落地。
接口顶部原始条件（未做资格推断）
{"city_list": [{"code": "CT_154", "en_name": "Wuhan", "i18n_name": "武汉", "location_type": 3, "mdm_code": "MDCY00000216", "name": "武汉", "node_status": 1, "py_name": "wuhan"}, {"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: 64aa9fde-b8af-41e7-a3d2-e89cff3b9830

`anm openings save --id 64aa9fde-b8af-41e7-a3d2-e89cff3b9830`