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

Open nowPosted 53 days ago

资深 Agent 工程师（Tripo Studio · Canvas Agent）

a9ihi0un9c/fte134 open roles

Where
Beijing, Chinese Mainland
Get the CV for this job

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

Your applicationOpen now资深 Agent 工程师（Tripo Studio · Canvas Agent）a9ihi0un9c/fte · 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 a9ihi0un9c/fte'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 53 days ago

The posting

【我们在做什么】 Tripo 做 3D 生成：把文本、图片和交互变成可交付的 3D 资产。https://tripo3d.ai

本岗位在 Agent 团队，负责 Studio 中的 Canvas Agent：把自然语言、参考图和画布操作，编排成可执行的创作流程。

工作重点是 Agent 架构、评测，以及效果、成本、时延之间的取舍。

【你将负责】 1. 端到端创作链路：基于自然语言、参考图和画布交互，规划并执行「生成 → 检查 → 分割 / 局部编辑 → 贴图 → 重拓扑 → 绑骨 → 导出」，交付可恢复、可评测的生产级资产。 2. Agent 架构演进与工具化：把 Studio 已有的生成与后处理能力，沉淀为稳定、可组合的 Tool / Skill / MCP；演进编排与控制循环，定义接口契约、权限边界、计量计费和失败语义。 3. 画布上下文：设计画布侧状态协议，把场景图、部件选中、相机位姿、编辑历史与当前任务纳入 Agent 决策，并与对话上下文统一编排。 4. 长程任务状态机：覆盖提交、排队、预览、取消、重试、换种子重跑和断点恢复；处理超时、部分成功和失败恢复，而不是只对接同步 API。 5. 效果、成本与时延的取舍：这是一组持续 trade-off，不是单向追精度。按资产用途在快速网格与高精度模型之间路由，抑制无效重试；依据模型能力边界做选型、工具划分和停止条件，而不是默认调用最强模型。 6. 评测、triage 与效能：建设离线评测集和在线指标；对失败与低采纳 case 做 triage，把调优做成可重复迭代，持续提升效果、成本和时延上的效能。用户采纳、重生成、局部修改和导出用途，作为数据飞轮输入。 7. 跨团队落地：与前端、后端、算法、评测和 Infra 对齐接口、状态协议与交付节奏，把 Canvas Agent 稳定推到线上。

【任职要求】 1. 本科及以上学历，计算机相关专业；3 年及以上后端或平台开发经验，能独立定位线上故障并做性能治理。 2. 精通 Go，有服务端系统设计与落地经验；能独立完成高并发与异步任务架构。熟悉缓存、消息队列、限流、熔断、降级与灰度；熟悉 Docker / Kubernetes、PostgreSQL、Redis。 3. 有 AI / Agent 相关的生产实践：做过线上质量、工作流、模型调用或同类系统即可。掌握意图理解与澄清、工具调用（Function Calling / MCP / Skill）、记忆与上下文压缩；能独立讲清并实现 Agent Loop，不绑定单一框架。 4. 理解 Agent 控制循环与系统拓扑的分工。熟悉 ReAct、Plan-Execute、Critic / Reflection 等循环，能判断观察是否改写下一步、何时打回、何时终止，并区分探索循环与步骤已锁定的定稿生成。熟悉 Router / Pipeline / Orchestrator 等拓扑，能设计产物与权限在节点间的交接，避免循环正确但交接失败、整链重跑。 5. 有 Agent Infra 生产实践：能落地模型网关、多模型路由、用量与成本控制、链路追踪与回放。能讲清 Runtime 在生产里承担什么、不承担什么，不把「会调框架 API」当成 Runtime 能力本身。 6. 能对线上坏结果做 triage，定位是规划、工具、模型、上下文还是停止条件的问题；能据此调优，并用 eval 和效能指标验证，而不是只看链路是否跑完。持续跟踪前沿模型与 Agent 工程实践。

【加分项】（按匹配度） 1. 熟悉主流 Agent Runtime 框架（如 Eino、Google ADK），并有生产使用经验。 2. 有 2D / 3D 创作 Agent，或图像 / 视频 / 3D 生成工作流编排经验（如 ComfyUI、DCC 插件、节点式画布）。 3. 有 VLM / 多模态 Agent 经验，能基于视觉反馈驱动下一步编辑。 4. 有 MCP / Skill / CLI 设计经验，能向其他 Agent 或 IDE 暴露稳定工具协议。 5. 有 Agent 评测集建设，或把用户行为闭环为数据飞轮的实践。 6. 有向量检索、会话记忆或项目级记忆的工程实践。

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 a9ihi0un9c/fte'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 a9ihi0un9c/fte'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

    a9ihi0un9c/fte'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.