知乎AI Infra 工程师（大模型训练/推理框架）
社招全职3年以上地点：北京状态：招聘♡ 收藏
工作描述
岗位职责 1. 推理适配与优化：基于 vLLM、SGLang、TensorRT-LLM 等框架，在 NVIDIA Blackwell 平台上适配主流开源模型；通过并行策略、PD 分离、KV Cache 复用、投机解码等手段优化吞吐与延迟，支撑 MaaS 平台上线，降低单位 token 成本。 2. 训练适配与优化：基于 Megatron-Core、FSDP 及 verl、OpenRLHF 等框架，支持租户的预训练、SFT 及 RLHF/GRPO 等任务，优化多机训练效率。 3. 镜像与版本管理：维护官方训练/推理镜像，跟进 CU…
登录查看完整工作描述
微信扫码，1秒登录
包括英文材料
大模型+
https://www.youtube.com/watch?v=xZDB1naRUlk
You will build projects with LLMs that will enable you to create dynamic interfaces, interact with vast amounts of text data, and even empower LLMs with the capability to browse the internet for research papers.
https://www.youtube.com/watch?v=zjkBMFhNj_g
vLLM+
https://www.newline.co/@zaoyang/ultimate-guide-to-vllm--aad8b65d
vLLM is a framework designed to make large language models faster, more efficient, and better suited for production environments.
https://www.youtube.com/watch?v=Ju2FrqIrdx0
vLLM is a cutting-edge serving engine designed for large language models (LLMs), offering unparalleled performance and efficiency for AI-driven applications.
SGLang+
[英文] Install SGLang
https://docs.sglang.ai/get_started/install.html
SGLang is a fast serving framework for large language models and vision language models.
https://github.com/sgl-project/sgl-learning-materials
TensorRT+
https://docs.nvidia.com/deeplearning/tensorrt/latest/getting-started/quick-start-guide.html
This TensorRT Quick Start Guide is a starting point for developers who want to try out the TensorRT SDK; specifically, it demonstrates how to quickly construct an application to run inference on a TensorRT engine.
缓存+
https://hackernoon.com/the-system-design-cheat-sheet-cache
The cache is a layer that stores a subset of data, typically the most frequently accessed or essential information, in a location quicker to access than its primary storage location.
https://www.youtube.com/watch?v=bP4BeUjNkXc
Caching strategies, Distributed Caching, Eviction Policies, Write-Through Cache and Least Recently Used (LRU) cache are all important terms when it comes to designing an efficient system with a caching layer.
https://www.youtube.com/watch?v=dGAgxozNWFE
Megatron+
https://www.youtube.com/watch?v=hc0u4avAkuM
FSDP+
https://docs.pytorch.org/tutorials/intermediate/FSDP_tutorial.html
In DistributedDataParallel (DDP) training, each rank owns a model replica and processes a batch of data, finally it uses all-reduce to sync gradients across ranks.
https://www.youtube.com/watch?v=PjEwLgyzuzQ
FSDP provides a comprehensive framework for large model training in PyTorch.
RLHF+
[英文] What is RLHF?
https://aws.amazon.com/what-is/reinforcement-learning-from-human-feedback/
Reinforcement learning from human feedback (RLHF) is a machine learning (ML) technique that uses human feedback to optimize ML models to self-learn more efficiently.
https://www.ibm.com/think/topics/rlhf
Reinforcement learning from human feedback (RLHF) is a machine learning technique in which a “reward model” is trained with direct human feedback, then used to optimize the performance of an artificial intelligence agent through reinforcement learning.
SFT+
https://cameronrwolfe.substack.com/p/understanding-and-using-supervised
Understanding how SFT works from the idea to a working implementation...
还有更多 •••
相关职位
社招1年以上搜一搜技术
1.具备较强的动手能力；熟悉 Python ，具备扎实的系统编程功底和优秀的复杂系统 Debug 能力； 2.深入理解大模型分布式训练原理，具备 Megatron-LM、DeepSpeed 或 Py
更新于 2026-10-13广州
社招3-5年J0012
1、有大数据引擎（Spark&Flink）、大模型训练AI-Infra优化经验优先，参与过大规模分布式系统开源贡献，或在相关领域有论文产出者加分； 2、熟悉K8S&了解Yarn调度，熟悉机器学习相关技
更新于 2025-11-14北京
社招3年以上
岗位要求： ● 有3年以上大模型训练经验 ● 有算法研究经验 ● 精通大模型分布式训练框架（包括但不限于： megatron、nemo、deepspeed、dspark等等） ● 扎实的编程能力（
更新于 2026-08-06杭州
社招1年以上技术-基础平台
1. 计算机、软件工程等相关专业本科及以上学历，2 年以上容器、云原生或大规模基础设施研发经验。 2. 熟练掌握 Go 语言，具备扎实的 Linux 系统基础（网络栈、文件系统、cgroups、进程管
更新于 2026-11-03北京|深圳|上海