Skip to content

Open nowPosted 255 days ago

算法工程师 - Agent

kaonai/index37 open roles

Where
Beijing, Chinese Mainland
Get the CV for this job

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

Your applicationOpen now算法工程师 - Agentkaonai/index · Beijing, 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 kaonai/index'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.

12.1% 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. 4.5%3 days
  3. 12.1%7 days
  4. 19.1%14 days
  5. 35.6%30 days
  6. 52.7%60 days
This job: posted 255 days ago

The posting

负责公司AI Agent方向的算法研究与落地工作,围绕个性化内容生成与长期记忆构建,将大模型训练技术(SFT、RL等)应用于Agent能力的持续提升,具体职责包括但不限于:

1. Agent架构设计:面向个性化内容生成和角色交互场景,设计并实现基于大语言模型的Agent架构;定义Agent的编排流程、工具调用(Tool Use)、反思(Reflection)等核心范式,使Agent能够基于用户画像和历史交互生成高度个性化的内容与回复 2. Agent训练与优化:运用SFT、RFT、PPO、DPO、GRPO等训练方法,针对Agent场景设计专项训练方案;构建Agent行为轨迹数据集,通过强化学习优化Agent的个性化生成质量、记忆调用准确性和多轮对话一致性 3. 训练环境设计:构建Agent训练所需的真实可执行交互环境(工具调用沙箱、用户模拟器、多轮对话场景等),定义状态空间、动作空间和反馈信号,为Agent提供高质量的训练闭环 4. 奖励建模:设计Agent专用的奖励函数与评估体系,针对个性化程度、内容一致性、记忆调用准确性、用户满意度等多维目标,结合过程奖励模型(PRM)、生成式奖励模型(GRM)以及个性化奖励模型(Personalized RM,基于用户偏好和交互历史动态调整奖励信号),实现对Agent行为链路的细粒度奖励,解决奖励稀疏、奖励欺骗等核心难题 5. 记忆与个性化系统:构建可解释、可迁移、可控的Agent记忆架构,支持用户偏好的长期建模与动态更新;实现记忆的版本化管理,支持精确遗忘(通过token删除)和跨模型迁移,保障个性化体验的连续性与可控性 6. 持续学习(Continual Learning):研究并实现Token Space下的持续学习机制,通过更新Agent的learned context(系统提示、记忆库、工具定义等)而非模型权重来实现Agent的持续进化;解决context poisoning(上下文污染)/ context rot(上下文退化)等有限上下文窗口下的记忆退化问题,在避免灾难性遗忘的前提下实现Agent知识的增量积累 8. 快速实验与迭代闭环:具备从eval构建、数据准备、方案实现到结果评估的全链路快速实验能力;参与Agent的线上A/B实验设计,通过线上效果度量和用户反馈分析定位算法瓶颈,驱动下一轮训练与模型优化的方向

1. 优秀的代码能力、数据结构和基础算法功底,熟练C/C++或Python,ACM/ICPC、NOI/IOI、Top Coder、Kaggle等比赛获奖者优先; 2. 熟悉NLP相关的算法和技术,具备大模型训练和RL算法的实践经验; 3. 对LLM-based Agent系统有深入理解,具备Agent训练或Agent系统相关的项目经验; 4. 能系统性拆解Agent在长期记忆管理、个性化内容生成、上下文窗口利用等场景的挑战,提出创新解决方案; 5. 具备较强自驱力,能与产品、算法团队紧密协作,推动技术从研究到落地的全链路闭环。

加分项: 1. 在Agent记忆机制、个性化生成、持续学习、上下文优化(如DSPy等prompt optimization方法)等方向有论文成果; 2. 对continous learning、memory-augmented LLM、Agent环境/奖励设计等前沿方向有研究或实践经验; 3. 有构建Agent RL训练环境(可执行环境、用户模拟、工具调用仿真等)的实践经验。

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 kaonai/index'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 kaonai/index'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

    kaonai/index'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.