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

Open nowPosted 103 days ago

融合模型算法实习生

bqsz5qltsd5/index24 open roles

Where
Shanghai, Chinese Mainland
Get the CV for this job

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

Your applicationOpen now融合模型算法实习生bqsz5qltsd5/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 bqsz5qltsd5/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. 57.8%60 days
This job: posted 103 days ago

The posting

关于这个项目 我们正在构建一个面向复杂任务的模型融合系统。它不是简单地接入单个大模型，而是通过构建多模型并行生成、候选答案分析、强模型合成、智能路由策略、流式输出与可观测评测的完整闭环，让不同模型在推理、代码、研究、工具调用等场景中形成深度互补。 这个方向的核心命题并非“哪个模型最强”，而是如何稳定、可解释、可复现地组织多模型能力，并在质量（Quality）、成本（Cost）、延迟（Latency）之间做出极致的工程化权衡。 我们正在寻找一位能参与完整工程闭环的工程师——从 Benchmark 设计、实验执行、问题归因，到系统设计调整、核心代码实现与验收指标沉淀。

你会负责 核心系统开发：参与模型融合 Gateway、评测 Harness（测试框架）、实验 Runner、Trace/Observability（链路追踪与可观测性）等核心系统的设计与实现。 • 评测体系建设：设计与维护开发 Benchmark，覆盖代码生成、研究问答、终端操作、工具调用（Tool Calling）、多模型融合策略等关键能力维度。 • 实验与分析：跑模型组合、Scaffold（生成框架）、Routing（路由）、Reasoning 转发、Timeout/Fallback（超时与降级）等对照实验，深度分析质量、成本、延迟与稳定性指标。 • 问题归因与闭环：结合 Trace 链路、模型原始输出与用户反馈，精准定位系统失败根因，并将问题转化为可复现的 Case 和具体的工程改进项。 • 策略优化：优化融合链路中的关键环节，包括候选生成、分析摘要、合成输入构造、流式处理、Partial Salvage（部分结果抢救）、自动评分与验收逻辑。 • 知识沉淀：输出清晰的实验记录、架构设计文档和可验证的结论，让团队能基于数据持续迭代系统。

我们希望你具备 扎实的编码能力：拥有 Rust / Python / TypeScript 中至少一种语言的实际开发经验，并愿意根据项目需要灵活补齐技术栈。 • 重度 AI 用户：对模型行为、Agent（智能体）、Eval Harness、Benchmark、Tool Calling、Streaming（流式传输）、上下文结构等底层细节有浓厚兴趣。 • 独立性与灵活性：能独立设计和实现模块，也能坦然接受实验结果与预期不符，并据此调整系统设计。 • 数据驱动习惯：愿意写脚本、跑对照实验、深挖 Trace 和分析失败样本，不凭直觉拍板。 • Benchmark 怀疑精神：时刻关注 Case 质量、评分标准合理性、数据泄漏风险、过拟合、评测代表性和可复现性。 • 成本与延迟意识：理解模型系统不能只追求单点质量峰值，必须时刻关注吞吐量、响应时间、服务稳定性和 API 调用成本。 • 扎实的工程素养：重视代码质量、单元测试、技术文档、可维护性以及变更的可回滚性。

加分项 -做过 LLM、RAG、Agent、评测系统、开发者工具、IDE 插件、代码生成工具或自动化测试平台。 • 熟悉 OpenAI-compatible API、Responses API、SSE Streaming、Tool Calling、Reasoning Content 等接口细节。 • 具备 Async Rust（Axum/Tokio）、Python Eval Pipeline、CLI 工具或前端实验看板 的开发经验。 • 有过 Benchmark 设计、自动评分、人工评审、Ablation（消融实验）、误差分析或模型对比实验 的经验。 • 能阅读模型、Agent、Eval 相关的前沿论文或开源实现，并将其转化为可验证的工程实验。

我们不特别看重 • 年龄、学历标签或大厂经历。 • 是否有非常标准的“AI 岗位”过往 Title。 • 是否已经完整做过一模一样的同类系统。 我们更看重你解决问题的思路、对技术的热情，以及在复杂系统中寻找确定性的能力。

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 bqsz5qltsd5/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 bqsz5qltsd5/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

    bqsz5qltsd5/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.