小红书【REDstar】大模型 Infra 工程师
校招全职地点:北京 | 上海 | 杭州状态:招聘♡ 收藏
工作描述
任职要求 任职资格: 1、具备扎实的代码能力、数据结构和基础算法功底,熟悉 Python / C++ / Rust 中至少一门语言,具备良好的工程实现能力和代码质量意识。 2、在大模型训练、推理或模型压缩至少一个方向具备深入实践,能够阅读和修改框架源码,并有性能优化或生产级工程落地经验。 3、熟悉至少一种主流训练、后训练或推理框架,如 PyTorch、Megatron、DeepSpeed、veRL、OpenRLHF、TRL、vLLM、SGLang、TensorRT-LLM、Nvidia Dynamo、AIBrix 等,并具备使用或二次开发经验。 4、理解分布式训练或推理的核心技术,包括并行策略、显存管理、跨机通信、KV Cache、请求调度、服务稳定性等;无需同时精通全部方向,但能够基于系统原理分析和解决复杂问题。 5、具备性能分析和问题定位能力,能够借助 Nsight Systems / Compute、PyTorch Profiler、日志、监控和实验分析等手段定位计算、通信、显存或系统瓶颈,并推动问题闭环。 6、能围绕吞吐、延迟、并发、稳定性、资源利用率、精度、成本和业务效果等指标进行系统分析,在技术效果与业务收益之间做出合理权衡。 7、具备良好的学习能力、沟通协作能力、自驱力和问题闭环意识,能够与算法、平台及业务团队协同推进技术落地。 加分项: 1、在大模型训练、推理、模型压缩、分布式系统或 MLSys 方向有高水平论文发表或优秀开源项目经历。 2、有千卡级大模型训练、后训练或大规模线上推理实战经验,解决过跨节点通信、显存优化、容错训练、高并发、故障迁移、弹性扩缩容或 SLO 保障等生产问题。 3、参与过 Megatron、DeepSpeed、veRL、OpenRLHF、vLLM、SGLang、TensorRT-LLM、Nvidia Dynamo、AIBrix 等开源项目的核心模块开发或贡献。 4、有 CUDA Kernel、Fuse…
登录查看完整工作描述
微信扫码,1秒登录
包括英文材料
学历+
算法+
https://roadmap.sh/datastructures-and-algorithms
Step by step guide to learn Data Structures and Algorithms in 2025
https://www.hellointerview.com/learn/code
A visual guide to the most important patterns and approaches for the coding interview.
https://www.w3schools.com/dsa/
数据结构+
https://www.youtube.com/watch?v=8hly31xKli0
In this course you will learn about algorithms and data structures, two of the fundamental topics in computer science.
https://www.youtube.com/watch?v=B31LgI4Y4DQ
Learn about data structures in this comprehensive course. We will be implementing these data structures in C or C++.
https://www.youtube.com/watch?v=CBYHwZcbD-s
Data Structures and Algorithms full course tutorial java
C+
https://www.freecodecamp.org/chinese/news/the-c-beginners-handbook/
本手册遵循二八定律。你将在 20% 的时间内学习 80% 的 C 编程语言。
https://www.youtube.com/watch?v=87SH2Cn0s9A
https://www.youtube.com/watch?v=KJgsSFOSQv0
This course will give you a full introduction into all of the core concepts in the C programming language.
https://www.youtube.com/watch?v=PaPN51Mm5qQ
In this complete C programming course, Dr. Charles Severance (aka Dr. Chuck) will help you understand computer architecture and low-level programming with the help of the classic C Programming language book written by Brian Kernighan and Dennis Ritchie.
C+++
https://www.learncpp.com/
LearnCpp.com is a free website devoted to teaching you how to program in modern C++.
https://www.youtube.com/watch?v=ZzaPdXTrSb8
CUDA+
https://developer.nvidia.com/blog/even-easier-introduction-cuda/
This post is a super simple introduction to CUDA, the popular parallel computing platform and programming model from NVIDIA.
https://www.youtube.com/watch?v=86FAWCzIe_4
Lean how to program with Nvidia CUDA and leverage GPUs for high-performance computing and deep learning.
分布式系统+
https://www.distributedsystemscourse.com/
The home page of a free online class in distributed systems.
https://www.youtube.com/watch?v=7VbL89mKK3M&list=PLOE1GTZ5ouRPbpTnrZ3Wqjamfwn_Q5Y9A
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
Triton Inference Server+
https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html
Triton Inference Server is an open source inference serving software that streamlines AI inferencing.
NCCL+
https://developer.nvidia.com/nccl
The NVIDIA Collective Communication Library (NCCL) implements multi-GPU and multi-node communication primitives optimized for NVIDIA GPUs and networking.
Megatron+
https://www.youtube.com/watch?v=hc0u4avAkuM
DeepSpeed+
[英文] Getting Started
https://www.deepspeed.ai/getting-started/
DeepSpeed model training is accomplished using the DeepSpeed engine.
https://www.youtube.com/watch?v=pDGI668pNg0
LLaMA-Factory+
https://llamafactory.readthedocs.io/en/latest/
LLaMA Factory is an easy-to-use and efficient platform for training and fine-tuning large language models.
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
LMDeploy+
https://lmdeploy.readthedocs.io/en/latest/get_started/get_started.html
This tutorial shows the usage of LMDeploy on CUDA platform.
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.
ONNX+
https://github.com/onnx/tutorials
Open Neural Network Exchange (ONNX) is an open standard format for representing machine learning models.
[英文] Introduction to ONNX
https://onnx.ai/onnx/intro/
This documentation describes the ONNX concepts (Open Neural Network Exchange).
还有更多 •••
相关职位
校招
1、本科及以上学历,计算机等相关专业方向优先; 2、熟练掌握GPU CUDA编程; 3、熟练掌握Megatron/DeepSpeed/FSDP等框架的研发,熟练掌握模型并行分布式技术; 4、对大语言模
更新于 2026-08-24北京|上海
校招
1、本科及以上学历,计算机等相关专业; 2、熟悉内容理解相关算法,了解内容理解在推荐系统中的落地链路;有相关项目/实习/科研经验,有增长场景实践经验者优先; 3、具备强烈的业务 sense,善于将业务
更新于 2026-08-25北京|上海
校招
1、本科及以上学历,计算机等相关专业; 2、扎实的计算机基础,对程序分析、软件工程有深入理解; 3、具备优秀的代码能力、数据结构和基础算法功底,熟练掌握C/C++、Python等一个或多个编程语言;
更新于 2026-09-03北京|上海