Skip to content
CV Rocket
Get started
How it worksThe enginePricingBlogContactSign in

Open nowPosted 191 days ago

Agentic RL For Long Horizon Task - 剪映CapCut

ByteDance19,269 open roles

Where
Beijing, Chinese Mainland
Get the CV for this job

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

Your applicationOpen nowAgentic RL For Long Horizon Task - 剪映CapCutByteDance · 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 ByteDance'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. ByteDance postings stay open a median of 9 days.

Share of postings closed within
  1. 2.0%1 day
  2. 4.3%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 191 days ago

ByteDance median: 9 days open

The posting

团队介绍：剪映研发团队，主要支持剪映、CapCut、醒图、Hypic、即梦、Dreamina、小云雀、Pippit等多款国内外产品的研发工作，业务覆盖多元化影像创作场景，并孵化了多款AIGC明星产品，相关产品多次登顶国内外App Store 免费应用榜第一，并继续保持高速增长。加入我们，一起打造全球最受用户欢迎的影像创作和GenAI产品。

课题介绍： Seedance2.0发布后，创作Agent进入深水区，无论是漫剧/短剧/视频/图片都有新的飞跃，为了快速满足用户高质量的创作需求，尤其是超过15s的成片，需要一个涉及多轮Function Call的创作Agent去完成，涉及大量工具的调用，包括不限于意图，分镜，创意，故事性，故事版等。我们打造基于Agentic RL的Agent赋能业务。 Agentic RL在训练 Long-Horizon Tasks有一系列核心难点，本质上比传统RL更复杂，“Agent”不仅要行动，还要规划、分解任务、记忆上下文。 具体难点： 1、Sparse Rewards； 2、Credit Assignment； 3、Planning & Decomposition； 4、Huge State Space； 5、Memory； 6、Exploration； 7、Optimization Difficulty； 8、复杂的Agent交互环境 我们需要解决Agentic RL在多轮Function Call，多个Tools和Skills下的长任务训练问题。

课题挑战： 1、Sparse Rewards a、稀疏奖励，如何设计合理的奖励 2、Credit Assignment a、如何解决信用分配问题 3、Planning & Decomposition a、如何拆解子目标 b、子目标的合理性 4、复杂的Agent交互环境 a、特别长的上下文 b、很多的Tools or Skills 5、训练的稳定性 a、同步、异步RL b、Rollout效率

课题价值： 技术价值： Agentic RL在Long Horizon Task是业内公认的难题，是处理复杂任务，Agent任务必须要攻克的难题，是提升大模型Agent效果上限的关键难题。

业务价值： 1、Long Horizon Task的解决会极大提升剪映各创作agent在处理长任务时的效果，使自研模型对比基座取得行业SOTA； 2、该技术的突破，可以落地更多更复杂的业务场景，尤其对目前的Sandbox Skill等架构有天然的适配。

1、2027届毕业，获得博士学位，人工智能、计算机科学、数学相关专业优先； 2、技术能力： 1）具备出色的编程能力，精通Python/C++，熟悉TensorFlow/PyTorch等框架，有自然语言处理（NLP）、计算机视觉（CV）或多模态生成模型（如CLIP、Diffusion Models）项目经验； 2）熟悉AIGC工具链（LangChain、AutoGPT）者优先； 3）熟悉大模型理论知识和应用，熟悉常见大模型架构，理解实际业务场景Agent设计理念；有实际大模型预训练、微调或推理优化经验者优先； 3、学术与实践经验： 1）在ACL/CVPR/SIGIR/KDD/NeurIPS/ICCV等顶会发表过AIGC、LLM等相关论文者优先； 2）了解LLM架构，熟悉Multi-Agent技术、Prompt/Context Engineering工程技术，有AI Agent应用经验、AIGC实操经验的优先； 3）热爱视频剪辑，对常用视频剪辑工具有使用经验者优先。

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 ByteDance'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 ByteDance'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

    ByteDance'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.

Get the CV for this 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.