Skip to content

Open nowPosted 11 hours ago

后训练数据算法工程师(VLA / 具身智能方向)

nwd4iy9rd2s/referral79 open roles

Where
Beijing, Chinese Mainland
Get the CV for this job

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

Your applicationOpen now后训练数据算法工程师(VLA / 具身智能方向)nwd4iy9rd2s/referral · 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 nwd4iy9rd2s/referral'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.

13.1% of postings close within 7 days. Measured by our own scanner across the market. nwd4iy9rd2s/referral postings stay open a median of 6 days.

Share of postings closed within
  1. 2.2%1 day
  2. 4.7%3 days
  3. 13.1%7 days
  4. 21.1%14 days
  5. 35.8%30 days
  6. 59.0%60 days
This job: posted 11 hours ago

nwd4iy9rd2s/referral median: 6 days open

The posting

职位描述 负责 VLA 具身模型后训练阶段的数据体系建设与算法研发,面向 SFT、DPO、RLHF/RLAIF 等后训练范式,搭建高质量后训练数据生产、筛选、编排、评估闭环,支撑具身大模型对齐与能力迭代。 后训练多模态数据质量建模:针对视频、图像、机器人状态、动作轨迹、指令、反馈偏好等时序多模态数据,做一致性校验、时序对齐、噪声 / 坏样本识别、隐私脱敏,建立适配后训练目标的可解释质量打分、错误归因体系,区分指令歧义、动作不合理、轨迹矛盾、图文不匹配等问题。 后训练样本自动标注与增强算法:基于 VLM、视频理解模型研发自动化标注工具链,实现指令改写、偏好对构建、轨迹重描述、结果评判、正负样本构造、困难样本增广,落地 SFT / 偏好数据的自动化生产,降低人工标注成本。 面向后训练目标的高价值样本挖掘:从原始采集数据、模型 rollout 回放数据中挖掘高冲突、高难度、长尾、边界、失败轨迹样本;开发多模态检索、表征聚类、去重、难度评估、偏好价值打分算法,优化后训练数据采样策略。 数据分布与编排优化:围绕场景 × 任务 × 物体 × 动作 × 失败类型 × 偏好维度建立后训练数据分布矩阵,量化数据覆盖度、分布偏移、正负样本配比、难度分层;开发数据混排、课程式采样、动态配比算法,输出分布监控看板。 数据 - 模型对齐闭环迭代:协同 VLA 模型、后训练对齐团队,分析 SFT/DPO/RL 阶段模型收益、过拟合、泛化衰减、任务失败 case,反向定位数据缺陷、分布缺口、偏好矛盾;驱动数据采集、过滤、增强、重标注策略持续迭代,打造后训练数据飞轮。

职位要求 本科及以上,计算机、人工智能、自动化、机器人、数学等相关专业 熟练 Python,精通 PyTorch/TensorFlow 任一深度学习框架,熟悉多模态数据处理、模型训练流程 熟悉 VLM、视频理解、多模态大模型、VLA 具身模型;理解 SFT、DPO、偏好学习、对比学习、表征检索、异常检测等相关技术 能够独立完成问题定义、算法设计、实验验证、指标评估、链路落地全流程,擅长跨团队协同对齐模型侧需求 熟练使用 AI Coding、Agent 开发工具提升算法迭代效率 加分项 有 SFT/DPO/RLHF/RLAIF 后训练数据、偏好数据构建经验;机器人具身、仿真 rollout、自动驾驶时序多模态数据处理经验;大规模大模型数据清洗、数据配比、课程采样、数据飞轮落地经验;VLM/VLA/ 世界模型 / 机器人学习相关项目;顶会论文、数据竞赛、相关开源贡献。 岗位价值 负责 VLA 具身模型后训练对齐阶段的数据智能体系,决定 SFT / 偏好数据的质量、分布与难度编排,直接影响模型指令跟随、任务鲁棒性、偏好对齐效果以及实体机器人上的零样本泛化与复杂任务成功率。

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 nwd4iy9rd2s/referral'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 nwd4iy9rd2s/referral'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

    nwd4iy9rd2s/referral'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.