Skip to content

Open nowPosted 102 days ago

大模型推理架构师

soulapp/index57 open roles

Where
Shanghai, Chinese Mainland
Get the CV for this job

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

Your applicationOpen now大模型推理架构师soulapp/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 soulapp/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. soulapp/index postings stay open a median of 1 days.

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 102 days ago

soulapp/index median: 1 days open

The posting

1. 参与 Soul 大模型、多模态模型、推荐模型等核心 AI 任务的训练与推理基础设施建设,提升模型从实验到线上部署的整体效率。 2. 负责大规模分布式训练系统的性能优化,包括数据并行、张量并行、流水线并行、专家并行、参数/梯度/优化器状态切分、显存优化、通信调度等方向,提升 GPU/NPU 集群利用率。 3. 参与高性能推理引擎建设,围绕大模型在线服务中的低延迟、高吞吐、弹性扩缩容、多租户隔离、KV Cache 管理、批处理调度、量化部署等问题进行系统优化。 4. 针对 Soul 的实时社交、多模态内容理解、AIGC 互动等场景,设计和优化端到端 AI 系统架构,降低训练和推理成本,保障核心业务的稳定性和体验质量。 5. 参与异构计算算子优化和计算图优化,包括 CUDA、Triton、CUTLASS、Ascend C、TileLang 等方向,针对 Attention、MoE、Embedding、推荐模型特征交互、多模态编码等关键模块进行性能调优。 6. 参与 AI 编译器和模型编译优化相关工作,围绕 IR 表达、算子融合、内存复用、调度优化、跨硬件后端适配等方向,提升模型在不同硬件平台上的执行效率。 7. 建设训练/推理性能分析、故障诊断、自动化调优、资源调度和可观测性工具,提升 AI 基础设施的工程效率与稳定性。 8. 跟踪并吸收业界前沿大模型系统技术,在合适的业务场景中完成工程化验证和落地。

1. 计算机基础扎实,熟悉操作系统、计算机体系结构、并发编程、网络通信、内存管理等底层知识,具备较强的问题定位和性能分析能力。 2. 熟练掌握 C/C++、Python,具备 CUDA、Triton、Ascend C、CUTLASS、CuTe DSL、TileLang 等一种或多种高性能计算开发经验。 3. 熟悉大规模分布式训练或推理系统,理解数据并行、张量并行、流水线并行、ZeRO/FSDP、MoE、Checkpoint、Offload、通信重叠等核心机制。 4. 熟悉 NCCL、NVSHMEM、RDMA、InfiniBand、RoCE、Verbs 等通信机制或工具链,有 GPU/NPU 集群通信优化经验者优先。 5. 熟悉主流深度学习框架和训练生态,包括 PyTorch、Megatron、DeepSpeed、FSDP、vLLM、SGLang、TensorRT-LLM、TorchInductor 等,有源码级优化经验者优先。 6. 熟悉 AI 编译器、计算图优化或异构计算工具链,包括 MLIR、LLVM、TVM、XLA、Triton Compiler、Torch Dynamo/Inductor 等相关技术者优先。 7. 具备扎实的工程能力,能够独立完成复杂系统问题拆解、性能瓶颈分析、方案设计、代码实现和线上验证。 8. 熟悉 Transformer、Diffusion、Embedding/Recommendation、Multimodal Encoder、MoE 等常见模型结构,能够理解模型结构对系统性能和资源使用的影响。

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 soulapp/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 soulapp/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

    soulapp/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.

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.