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

Open nowPosted 26 days ago

AI Agent Harness 工程师（Workspace / 端云协同 / 云端 Swarm）

acnc6zeentra/index41 open roles

Where
Shanghai, Chinese Mainland
Get the CV for this job

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

Your applicationOpen nowAI Agent Harness 工程师（Workspace / 端云协同 / 云端 Swarm）acnc6zeentra/index · 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 acnc6zeentra/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.

12.3% 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. 12.3%7 days
  4. 19.3%14 days
  5. 35.6%30 days
  6. 58.1%60 days
This job: posted 26 days ago

The posting

我们正在构建面向复杂任务的 AI Agent 执行平台，让 Agent 能够持续使用工具、管理工作空间、跨端执行，并通过多 Agent 协作完成长流程任务。你将负责核心 Harness 框架及相关基础设施，推动 Agent 在真实业务场景中可靠运行。 工作职责 1、设计与建设 Agent Harness 框架 负责 Agent 执行循环、模型接入、工具调用、上下文管理、状态持久化与生命周期管理。 建设任务暂停与恢复、取消、超时、重试和异常处理机制，提升长任务的执行可靠性。 设计清晰的协议、SDK 与扩展接口，支持不同模型、工具和业务 Agent 接入。 2、建设 Agent Workspace 设计统一的任务工作空间，管理代码、文件、依赖、执行环境与任务产物，为 Agent 提供持续工作的环境。 建设 Workspace 的创建、快照、恢复、回收与版本管理能力，支持长任务续接和执行过程追溯。 支持端云之间 Workspace 的同步与迁移，处理文件差异、环境依赖和产物一致性。 支持多 Agent 独立工作空间与共享资源协作，处理权限隔离、并发修改、变更合并和产物交付。 3、建设端云协同执行能力 打通桌面端、浏览器、本地开发环境与云端服务，实现任务分发、执行接管、上下文同步和产物交付。 处理断网重连、状态对账、重复执行与权限边界，确保任务跨端运行时行为可控、结果可追踪。 结合数据位置、设备能力、时延与成本，设计端云任务分工与调度策略。 4、建设云端 Swarm 多 Agent 系统 设计任务拆解、Agent 分工、并行调度、依赖管理、结果汇总和失败恢复机制。 建设多 Agent 通信、共享上下文与独立执行环境，处理协作冲突、资源竞争和任务收敛。 支持大规模任务的弹性执行、租户隔离、并发控制，以及 Token、时间和算力预算管理。 5、建立评估与持续改进体系 建设执行轨迹、日志、指标与回放能力，定位模型、工具、调度和环境中的失败原因。 围绕任务成功率、恢复能力、执行时延和成本建立评估及回归机制，推动真实业务场景落地。

任职要求 1、具备扎实的软件工程能力，熟练掌握 Go、Python、TypeScript、Rust 中至少一门语言，能够独立完成核心模块设计、开发和上线。 2、有 LLM Agent、执行框架或工具调用系统的实际开发经验，理解上下文管理、结构化输出、流式交互和模型调用的工程边界。 3、熟悉分布式系统基础，理解状态机、异步任务、消息队列、幂等、故障恢复与一致性问题。 4、熟悉文件系统、Git、依赖管理与执行环境管理，能够设计任务工作空间的隔离、持久化与协作机制。 5、有长任务或复杂工作流系统经验，能够分析部分失败、执行结果未知、取消与重试等场景。 6、具备良好的接口与抽象设计能力，能够在框架通用性、实现复杂度和交付效率之间做出合理取舍。 7、重视可观测性与验证，能够通过执行轨迹、实验和数据定位问题，持续改善系统表现。

加分项 1、有 Agent Harness、Agent Runtime、工作流引擎或分布式调度系统的建设经验。 2、有 Workspace、云端开发环境、沙箱、构建系统或远程执行平台开发经验。 3、有桌面客户端、浏览器自动化、Coding Agent 或本地工具执行环境开发经验。 4、有多 Agent 协作系统的实际落地经验，处理过并行任务协调、上下文隔离、变更合并与结果验证。 5、熟悉容器、Kubernetes、权限控制或多租户平台。 6、有 Agent 评测、轨迹分析、上下文压缩、推理成本优化经验，或相关开源贡献。

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 acnc6zeentra/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 acnc6zeentra/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

    acnc6zeentra/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.

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.