{"id":2734649,"url":"https://alion.io/job/hd-uijiansuanfagongchengshi","title":"推荐算法工程师","company":{"id":1977226,"name":"New Channel","domain":"xhd.cn","url":"https://alion.io/company/xhd","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Changsha, China"],"countries":["CN"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":15000,"max":40000,"currency":"CNY","period":"month","gross":null,"usd_annual":71928},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Claude","optional":false},{"name":"Claude Code","optional":false},{"name":"Context Engineering","optional":false},{"name":"Copilot","optional":false},{"name":"Cursor","optional":false},{"name":"DeepSeek","optional":false},{"name":"Function Calling","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"OpenAI","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"Qwen","optional":false},{"name":"RAG","optional":false}],"status":"live","first_seen_at":"2026-09-23T06:28:21Z","employer_posted_date":null,"last_verified_at":"2026-09-23T06:28:21Z","board_verified":false,"closed_at":null,"days_open":39,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":39},"description":"岗位职责：\n\n- 负责基于大模型、多模态模型的 AI 应用研发与落地，包括智能问答、企业知识库、内容生成、文档解析、题库理解、用户画像、个性化推荐及学习路径规划等场景。\n\n- 负责 Prompt Engineering、Context Engineering、RAG、Function Calling、Tool Calling、MCP、Agent Workflow、多 Agent 协作等核心能力建设。\n\n- 负责构建和持续演进 Agent 执行框架，围绕任务规划、工具调用、上下文管理、分层记忆、执行控制、异常恢复、人工反馈、结果评测和链路监控，提升 Agent 的可控性、稳定性与任务完成率。\n\n- 负责 Harness Engineering 体系建设，构建让模型自主迭代、优化代码链路的执行框架，包括代码生成、执行验证、结果评测、失败归因、策略调整与版本回滚，形成可闭环的 self-evolving 优化机制。\n\n- 负责设计 Agent 分层记忆架构，包括短期上下文记忆、长期用户记忆、知识库记忆、任务状态记忆、执行轨迹记忆和反馈记忆，并解决记忆提取、更新、召回、冲突与失效问题。\n\n- 负责企业级推荐系统的设计、开发和持续调优，覆盖召回、粗排、精排、重排及策略融合等环节，支持内容推荐、题目推荐、课程推荐、学习路径推荐等业务场景。\n\n- 负责用户画像、内容画像和特征体系建设，整合用户属性、行为序列、兴趣偏好、能力水平及实时上下文等信息，为推荐算法和 Agent 个性化决策提供支持。\n\n- 针对数据稀疏、冷启动、长尾分布、反馈偏差和兴趣漂移等问题，设计相应的推荐策略，并结合离线评测、在线实验、Badcase 分析和业务指标持续优化推荐效果。\n\n- 负责 AI 产品的服务端工程化建设，包括模型接入、模型网关、推理服务封装、API 开发、异步任务调度、权限控制、调用日志、Token 统计、成本控制和可观测性建设。\n\n- 熟练使用 Cursor、Claude Code、GitHub Copilot、Trae、通义灵码等 AI Coding 工具，完成需求分析、方案设计、代码生成、调试、重构、测试和文档编写。\n\n- 与产品、设计、算法、教研和运营团队协作，围绕业务目标快速完成 AI 与推荐功能的验证、评测、迭代和上线。\n\n任职要求：\n\n- 本科及以上学历，计算机、软件工程、人工智能、数据科学、数学等相关专业优先。\n\n- 熟悉 Python，具备良好的后端开发、数据处理、系统设计和 API 设计能力。\n\n- 具有实际 AI 应用开发经验，熟悉 OpenAI、Claude、DeepSeek、通义、豆包、Qwen、GLM 等一种或多种模型 API。\n\n- 理解 RAG、向量检索、Embedding、Prompt Engineering、Context Engineering、Function Calling、Tool Calling、MCP 和 Agent Workflow 等技术方案。\n\n- 理解 Agent 系统的完整闭环，包括模型、工具、记忆、任务规划、执行控制、结果评测、人工反馈和持续迭代。\n\n- 具备 Harness Engineering 思维，理解并实践让模型自主迭代优化代码链路的工程方法，能够围绕代码执行、评测反馈和失败案例构建 self-evolving 优化闭环。\n\n- 熟悉推荐系统基本架构与算法，理解协同过滤、内容推荐、Embedding 召回、向量检索、Learning to Rank、序列推荐及多路召回等常见方案。\n\n- 具备推荐算法调优能力，能够围绕召回率、排序效果、多样性、新颖性、覆盖率和业务转化等指标开展分析与优化。\n\n- 具备用户画像建设经验，能够设计用户标签、行为特征、兴趣特征、能力特征和实时特征，并将其应用于推荐、搜索或 Agent 个性化场景。\n\n- 具备企业级系统工程意识，能够处理高并发、服务稳定性、数据一致性、权限隔离、灰度发布、监控告警、成本控制和数据安全等问题。\n\n- 熟练使用至少一种 AI Coding 工具，能够在真实项目中使用 AI 辅助完成开发，并对生成代码进行验证、测试和质量控制。\n\n- 具备产品意识和业务理解能力，能够围绕实际业务指标设计 AI 与推荐能力，而非仅完成技术实现。","description_format":"text","description_chars":1791,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Education"],"lifecycle":[{"event":"open","at":"2026-10-16T18:37:00Z"}],"visa":[],"liveness":{"score":16,"band":"cold","label":"Long shot","p_open":0.6,"p_active":0.586,"p_room":0.45,"age_days":38,"expected_fill_days":24,"reasons":["seen:38","win:tail"],"computed_at":"2026-11-01T06:10:25Z"},"pay":{"stated_usd_annual":71928,"is_top_pay":false},"html_url":"https://alion.io/job/hd-uijiansuanfagongchengshi","json_url":"https://alion.io/job/hd-uijiansuanfagongchengshi.json","meta":{"generated_at":"2026-11-01T15:21:22Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":23463,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-02T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":1977226},"rest":"https://alion.io/mcp/rest/get_company?id=1977226"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fhd-uijiansuanfagongchengshi"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fhd-uijiansuanfagongchengshi"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fhd-uijiansuanfagongchengshi"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/hd-uijiansuanfagongchengshi\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fhd-uijiansuanfagongchengshi"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":2734649}},{"tool":"search_jobs","arguments":{"company":"xhd.cn","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":2734649},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}