Skip to content

Open nowPosted 97 days ago

蔚来AGI超星计划-企业智能算法研究员

nio/campus870 open roles

Where
Shanghai, Chinese Mainland
Get the CV for this job

From $25 per CV, paid once. No subscription.

Your applicationOpen now蔚来AGI超星计划-企业智能算法研究员nio/campus · Shanghai, Chinese Mainland
  1. YouYes, apply to this one.

  2. CV RocketCV written for this posting.

  3. 25 readersRecruiter, hiring manager, skeptic. Round after round.

  4. CV RocketApplied on nio/campus's own form.

The reply lands in your private mailbox

3×more interviews than doing it yourself with ChatGPT.

The clock on this job

Early applications get read.

11.5% of postings close within 7 days. Measured by our own scanner across the market.

Share of postings closed within
  1. 2.1%1 day
  2. 4.4%3 days
  3. 11.5%7 days
  4. 18.1%14 days
  5. 35.6%30 days
  6. 44.6%60 days
This job: posted 97 days ago

The posting

方向:Ontology / Context Engineering / Evaluation / Self-evolving AI 你要解决的问题 通用模型不会天然理解一家企业。 企业里存在数万张表、海量文档、复杂对象关系、不同指标口径、隐含规则和持续变化的业务状态。 这个岗位需要研究: 如何让 AI 从异构企业资产中建立语义,找到完整证据,组装正确上下文,完成可靠推理,并从失败中持续学习。 这不是单一的 RAG 问题,而是语义建模、信息检索、知识表示、推理、评测和学习系统的交叉问题。 你会参与的工作 1. 研究从表结构、字段、文档、代码和 API 中自动抽取企业对象、关系、事件、指标与规则; 2. 研究局部语义与 Canonical Ontology 的自动对齐、冲突识别和增量演进; 3. 设计面向复杂问题的多阶段召回、查询分解、证据选择和 Context Assemble 算法; 4. 研究结构化数据、非结构化知识和图谱的联合检索与 Rerank; 5. 建设 Context、Evidence、Agent、Skill 和业务输出的评测体系; 6. 从 tracing、用户反馈和业务结果中识别 badcase 根因,并生成资产修正建议; 7. 推动算法进入真实生产场景,并基于线上数据不断优化。 重点研究方向 1.1 Enterprise Ontology Induction - 从数仓 Schema、文档和代码中自动发现企业对象及关系; - Canonical Ontology 与领域 Ontology 的匹配、融合和冲突处理; - 弱监督、主动学习与专家反馈结合的语义治理; - Ontology 版本变化的影响分析与质量评估。 1.2 Semantic Mapping - 表、字段、指标、文档、API 与业务对象的跨模态语义匹配; - 基于描述、数据分布、查询日志和业务关系的联合建模; - Mapping 置信度、可解释性与人工审核优先级; - 面向长尾系统的小样本和零样本语义映射。 1.3 Context Assembly - Token 预算约束下的上下文选择和信息压缩; - 面向复杂任务的查询分解和多跳证据组装; - 事实、关系、规则、历史和 Memory 的动态组合; - 面向不同模型和任务的 Context 自适应优化; - Context 完整性、相关性、时效性和冗余度评价。 1.4 Evidence and Trustworthiness - 证据召回率、完整性和忠实度评测; - 结论与数据、文档、指标及规则之间的可验证绑定; - 无法回答、证据冲突和不确定性的识别; - 基于业务约束的幻觉检测和答案校验。 1.5 Agent Evaluation - 长链路任务的过程评测和结果评测; - Tool Call 正确性、任务完成度和执行风险评价; - 从 tracing 中定位失败发生在召回、推理、规划还是执行; - 基于生产 badcase 自动构建评测集; - Agent 版本回归与线上效果预测。 1.6 Governed Learning Flywheel - 从用户修正和业务结果中提取高价值学习信号; - 自动生成 Ontology、Mapping、Rule、Skill 和 Eval Case 的修改建议; - 防止错误反馈污染企业核心资产; - 人机协同下的受治理自进化机制; - 企业长期记忆的沉淀、压缩、冲突消解与遗忘。

我们希望你 - 来自人工智能、计算机、数学、统计学、信息检索、自然语言处理或相关专业; - 对研究问题有敏感度,不满足于调参和套用现成框架; - 具备扎实的机器学习、深度学习或信息检索基础; - 能阅读和复现高质量论文,也能把算法落到真实系统; - 熟练使用 Python、PyTorch 或主流机器学习工具; - 能够清晰定义问题、数据、指标、基线和实验方法。 加分项包括: - 在 NLP、IR、Knowledge Graph、Agent、LLM Evaluation、Database AI 等方向有研究经历; - 有论文、专利、竞赛、开源项目或高质量研究型项目; - 熟悉图学习、表示学习、Rerank、强化学习、因果推断或主动学习; - 有构建 benchmark、evaluation framework 或真实数据集的经验。

我们能提供什么 1. 真实而复杂的问题 你面对的不是公开数据集上的玩具任务,而是企业研发、供应链、制造、质量、财务和经营中的真实问题。 这些问题同时具备: - 数据规模大; - 资产类型复杂; - 权限约束严格; - 业务口径真实; - 错误成本高; - 研究价值和工程价值并存。 2. 从研究到生产的完整闭环 很多研究止步于离线指标,很多工程止步于功能上线。 在这里,你可以经历: 提出问题 → 建立数据集与基线 → 设计算法或系统 → 进入生产场景 → 收集 tracing 和 badcase → 验证真实业务价值 → 继续迭代 3. 足够大的个人责任边界 我们不希望优秀学生只承担边缘模块。 表现优秀的人可以直接负责: - 一项关键算法方向; - 一个核心产品模块; - 一条端到端技术链路; - 一个跨领域研究课题; - 一套公开 benchmark 或方法论。 4. 研究与公开成果机会 在满足企业安全和数据合规的前提下,我们支持将有普遍价值的问题沉淀为: - 学术论文; - 技术专利; - 公开 benchmark; - 开源框架或工具; - 高质量技术报告; - 行业标准和方法论。 我们不会为了论文而制造问题,但也不会让真正有研究价值的问题只停留在内部项目中。

我们寻找什么样的人 我们不只寻找履历最整齐的人。 我们更看重: - 是否能面对没有标准答案的问题; - 是否能快速进入陌生领域; - 是否有独立判断和研究品味; - 是否能把抽象想法变成可验证的系统; - 是否愿意对最终结果负责; - 是否既追求技术先进性,也理解真实业务约束。 AGI 超星计划不是为了招募更多执行者,而是寻找未来能够定义产品、定义系统、定义算法方向的人。

From $25, paid onceGet the CV for this job

What happens when you press

One press. We do the rest.

  1. A CV for this posting

    Written against nio/campus's own wording, from every piece of relevant proof in your profile.

  2. 25 readers review it

    Recruiter, hiring manager, skeptic and more read every draft, round after round. You get the best round.

    The review screen in CV Rocket: how each CV was read, round by round.
  3. We apply on nio/campus's form

    Our application engine gets through the hardest forms there are. Where a question needs you, AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

    An application in CV Rocket: every answer filled in on the employer's form.
  4. Every reply, sorted

    nio/campus's answer lands in your private mailbox, and we classify it on arrival: interview, question, rejection.

    The CV Rocket inbox: each employer reply classified as an interview, an action or a rejection.
  5. Reply with AI

    AI helps you write the email, checks it and sends it. We show you whether the recruiter read it.

  6. The interview in your calendar

    Full integration with your calendar. The invitation goes straight in.

    An interview invitation in the CV Rocket inbox, added to the candidate's calendar.
Get the CV for this job

From $25 per CV, paid once. No subscription.

Why it works

3×

more interviews than doing it yourself with ChatGPT.

ChatGPT writes a CV and never learns what happened to it. We see every reply. For each CV we know:

  • How it was written, and how the review scored it
  • When we applied, and how long after the posting went up
  • Which posting, which company, which city
  • Who got the interview, and who heard nothing

That is how we know which CVs get called.

Get the CV for this job

From $25 per CV, paid once. No subscription.

The numbers game

More applications. More interviews.

Every application goes out with its own CV, written for that posting and paid once. Send enough of them and the law of large numbers finds you the job.

By hand5–10
With CV Rocket100
applications a day

Nearby

Live postings like this one

Same employer first, then the same role elsewhere.

Before you press

Straight answers

Get the CV for this job

From $25 per CV, paid once. No subscription.

What if my background isn't good enough?

We make the most of the background you have. The CV uses every piece of relevant proof your profile holds, and one of the 25 readers reads your whole profile and flags what the CV left out.

Do you really apply for me?

Yes, on the employer's own form, the hardest ones included. Where a question needs you, you answer it right there and AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

Is it a subscription?

No. You pay once per CV, from $25. Every application goes out with its own CV, written for that posting.

One job. One CV.
Paid once.

Pick the posting you want. We write for it, apply for you and catch the reply.

Get the CV for this job

From $25 per CV, paid once. No subscription.