快手【留用实习】大模型推理/训练优化工程师
社招全职J1020地点：北京状态：招聘
任职要求
1、硕士及以上学历，计算机、电子、自动化等专业优先； 2、熟悉python/C++，熟悉linux使用，有扎实的算法与数据结构基础； 3、有较强的自驱力和学习力，有严谨的科研思维，沟通良好擅长与人合作； 4、了解AI infra 整体技术栈，有大模型相关训练或推理优化实战经验；有vLLM、TensorRT-LLM、MLC-LLM、Tensorflow、PyTorch等框架之一的实践经验。 加分项： 1、熟悉CUDA 或 ROCM，熟悉Nsight System/ Nsight Compute 工具的使用，有 GPU 或 ASIC 高性能算子开发经验； 2、熟悉深度学习编译优化或异构硬件，有 XLA/ TVM /MLIR 开发、优化经验，熟悉pass编写或代码生成原理和实践；或有传统编译器开发经验，熟悉LLVM原理和使用； 3、有相关领域顶会paper发表； 4、有二次开发能力或开源社区贡献经历。
工作职责
1、参与大模型推理/训练优化。通过研发业界领先的AI Compiler 技术，支撑搜推场景在GPU上的训练计算性能优化；支持大模型推理优化技术在异构硬件上的落地； 2、参与各种大模型推理所需的功能性开发任务；相关编译优化功能开发，以图优化、算子融合、GPU高性能算子开发及自动Codegen等技术手段不断推高在不同卡型上的计算性能极限； 3、参与支持日常的大模型推理服务部署，参与内部日常提效工具的研发。
包括英文材料
推荐系统+
[英文] Recommender Systems
https://www.d2l.ai/chapter_recommender-systems/index.html
Recommender systems are widely employed in industry and are ubiquitous in our daily lives.
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/
数据分析+
[英文] Data Analyst Roadmap
https://roadmap.sh/data-analyst
Step by step guide to becoming an Data Analyst in 2025
学历+
Python+
https://liaoxuefeng.com/books/python/introduction/index.html
中文，免费，零起点，完整示例，基于最新的Python 3版本。
https://www.learnpython.org/
a free interactive Python tutorial for people who want to learn Python, fast.
https://www.youtube.com/watch?v=K5KVEU3aaeQ
Master Python from scratch 🚀 No fluff—just clear, practical coding skills to kickstart your journey!
https://www.youtube.com/watch?v=rfscVS0vtbw
This course will give you a full introduction into all of the core concepts in python.
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
Linux+
https://ryanstutorials.net/linuxtutorial/
Ok, so you want to learn how to use the Bash command line interface (terminal) on Unix/Linux.
https://ubuntu.com/tutorials/command-line-for-beginners
The Linux command line is a text interface to your computer.
https://www.youtube.com/watch?v=6WatcfENsOU
In this Linux crash course, you will learn the fundamental skills and tools you need to become a proficient Linux system administrator.
https://www.youtube.com/watch?v=v392lEyM29A
Never fear the command line again, make it fear you.
https://www.youtube.com/watch?v=ZtqBQ68cfJc
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
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.
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.
TensorFlow+
https://www.youtube.com/watch?v=tpCFfeUEGs8
Ready to learn the fundamentals of TensorFlow and deep learning with Python? Well, you’ve come to the right place.
https://www.youtube.com/watch?v=ZUKz4125WNI
This part continues right where part one left off so get that Google Colab window open and get ready to write plenty more TensorFlow code.
PyTorch+
https://datawhalechina.github.io/thorough-pytorch/
PyTorch是利用深度学习进行数据科学研究的重要工具，在灵活性、可读性和性能上都具备相当的优势，近年来已成为学术界实现深度学习算法最常用的框架。
https://www.youtube.com/watch?v=V_xro1bcAuA
Learn PyTorch for deep learning in this comprehensive course for beginners. PyTorch is a machine learning framework written in Python.
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.
Nsight+
https://developer.nvidia.com/tools-tutorials
NVIDIA Nsight™ Developer tools are a suite of tools for building, profiling, and debugging accelerated applications.
https://www.youtube.com/watch?v=aQ1NYoRvp7o
Profile Python for AI and deep learning applications with NVIDIA's suite of Nsight Developer Tools.
https://www.youtube.com/watch?v=Iuy_RAvguBM
Join NVIDIA’s Jackson Marusarz for an introduction to NVIDIA Nsight Compute, a tool for in-depth analysis of CUDA kernel performance on GPUs.
深度学习+
https://d2l.ai/
Interactive deep learning book with code, math, and discussions.
LLVM+
https://llvm.org/docs/GettingStarted.html
Welcome to the LLVM project!
https://llvm.org/docs/tutorial/
This is the “Kaleidoscope” Language tutorial, showing how to implement a simple language using LLVM components in C++.
https://mcyoung.xyz/2023/08/01/llvm-ir/
“LLVM” is an umbrella name for a number of software components that can be used to build compilers.
https://www.youtube.com/watch?v=Lvc8qx8ukOI
This is the first lecture from the "Programming Language with LLVM" course where we build a full programming language similar to JavaScript from scratch, using LLVM compiler infrastructure.
相关职位
实习J1014
1、参与快手大规模深度学习推理引擎、大模型训练解决方案的研发与优化，包括大模型推理、模型训练框架、微调平台等； 2、参与底层算子的优化、通过优化访存pattern、计算提升推理性能，与算法部门合作，为公司大模型定制训练方案，探索RLHF、MoE、多模态、longcontext等前沿方向，提升训练性能； 3、优化推理框架上层调度策略，通过机内、机间的计算任务调度和通讯优化提升引擎性能；优化现有大语言模型相关工具和平台，提高模型训练、维护效率，降低成本，提升训练服务稳定性。
更新于 2025-05-23
实习J1020
1、参与研发业界领先的深度学习编译技术，落地计算优化、显存优化及分布式优化技术到训练框架和推理框架中，赋能深度学习算法落地； 2、XLA 相关编译优化功能开发； 3、结合pytorch/tensorflow等上下游框架适配与集成； 4、异构大模型推理引擎优化，负责调研NV 上各种推理引擎的优化技术，并支持大模型推理各种优化技术在异构硬件上的落地。
更新于 2025-05-14
实习J1020
1.参与AI与GPU相关项目的性能优化与研发，通过利用CPU、GPU的并行计算优化、架构优化、量化优化和异构调度等高性能优化技术，研发行业领先的高性能异构AI优化技术与编译优化技术； 2.针对搜索、推荐、广告、音视频以及大模型场景，优化模型训练和推理场景的性能； 3.与公司各算法部门深度合作，对重点项目进行算法与系统的联合优化。
更新于 2025-03-31
实习J1020
1. 负责分布式大语言模型 (LLM) 推理系统的底层基础设施研究与探索，包括 GPU 和 RDMA 等，提升 GPU 环境下的稳定性和计算效率； 2. 负责大规模模型训练场景优化工作，通过建设全面的异常发现、故障自愈机制，提升平台训练 MFU，降低训练成本； 3. 基于容器以及 Kubernetes 技术，负责对机器学习领域中的资源调度、模型训练、模型推理、数据管理等多个子方向的成本效率优化工作； 4. 持续关注并跟进业界技术发展，比如超长上下文、思维链、多模态方向；
更新于 2025-03-31