Skip to content

Open nowPosted 93 days ago

大模型算法工程师(压缩与轻量化方向) - PICO

ByteDance19,227 open roles

Where
Beijing, Chinese Mainland
Get the CV for this job

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

Your applicationOpen now大模型算法工程师(压缩与轻量化方向) - PICOByteDance · 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.

11.8% of postings close within 7 days. Measured by our own scanner across the market. ByteDance postings stay open a median of 2 days.

Share of postings closed within
  1. 2.1%1 day
  2. 4.4%3 days
  3. 11.8%7 days
  4. 18.6%14 days
  5. 35.6%30 days
  6. 45.1%60 days
This job: posted 93 days ago

ByteDance median: 2 days open

The posting

团队介绍:作为一家拥有自主创新和研发创造能力的科技品牌,PICO致力于成为领先的世界级XR平台,成就开发者与创作者,共同为全球消费者创造更美好的生活体验。我们开创性地将虚拟现实扩展到了多个领域,为运动、视频、娱乐等消费级场景带来了全新体验;并广泛应用在教育、医疗和企业培训等商用场景,给全球企业级用户提供了多元化的VR解决方案。

1、轻量化算法研发:主导大语言模型(LLM)及多模态模型的轻量化算法研究,包括量化(Quantization)、剪枝(Pruning)、稀疏化(Sparsity)与知识蒸馏(Knowledge Distillation),投机采样; 2、极低比特量化突破:设计并实现高效的后训练量化(PTQ)与量化感知训练(QAT)方案;深入探索低比特(INT8、INT4、FP8、NF4等)量化算法(如AWQ,GPTQ,SmoothQuant,OmniQuant等),在保证模型精度(Perplexity与下游任务准确率)的前提下逼近理论压缩极限; 3、结构精简与稀疏化:研究并落地基于Transformer架构的结构化/非结构化剪枝方案、层级丢弃(Layer Dropping)、注意力机制优化以及早期退出(Early Exit)机制,降低模型理论计算复杂度(FLOPs); 4、知识蒸馏链路构建:设计从千亿级Teacher模型向轻量级Student模型转移知识的蒸馏体系,包括LoGits蒸馏、中间特征/注意力矩阵蒸馏,以及基于特定领域指令微调(SFT)数据的自蒸馏机制; 5、精度损失分析与对齐:构建完善的模型轻量化评测体系,能够快速定位在压缩过程中产生精度坍塌或能力退化的根本原因(如异常值Outliers分布分析),并提出针对性的算法补偿策略。

1、获得硕士学位及以上,计算机、数学、人工智能或相关专业优先; 2、具备扎实的机器学习与数学理论基础;精通Python和PyTorch,能高效实现并复现复杂的深度学习算法; 3、深入理解Transformer架构的底层逻辑(Self-Attention,KV Cache,GQA/MQA,MoE机制,各类位置编码等); 4、具备丰富的模型压缩实战经验,主导或深度参与过大参数量模型的压缩项目; 5、对主流的大模型量化算法原理及其数学推导有深刻理解,清楚不同量化方案在处理权重(Weight)和激活值(Activation)时的优劣与边界; 6、具备较强的Paper阅读能力与严谨的实验分析习惯,能够从数据分布、模型梯度的微观层面分析轻量化带来的影响。

加分项: 1、在AI会议(ICLR,ICML,NeurIPS,ACL,EMNLP等)发表过模型压缩、高效AI(Efficient Inference/TinyML)相关的高质量论文; 2、深入阅读并修改过业界知名模型压缩库的源码,或向bitsandbytes,AutoGPTQ,AutoAWQ,vLLM(量化模块),Neural Magic等开源项目贡献过代码; 3、熟悉Megatron-LM、DeepSpeed等分布式训练框架,有在多机多卡环境下进行大规模QAT(量化感知训练)或大规模知识蒸馏的实操经验; 4、了解GPU(CUDA)或NPU的底层访存与计算特性,了解W4A16、W8A8等量化算子的实际硬件加速瓶颈(Memory-bound vs Compute-bound),具备“算法-硬件”联合设计的意识。

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.

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.