
地平线【2027届校招】模型推理优化工程师
校招全职软件序列地点:北京状态:招聘
工作描述
任职要求 我们需要的人 基本要求 1.2027 届本科及以上学历,计算机科学、人工智能、电子工程或相关专业 2.扎实的计算机基础:深入理解操作系统原理、计算机体系结构、数据结构与算法,对系统性能优化有直觉 3.在以下至少一个领域具备扎实基础: ①GPU / 高性能计算:CUDA 编程、算子优化、内存管理 ②分布式系统:一致性、调度、通信原理 ③大模型推理或训练系统:Serving 架构、并行策略、显存优化 4.优秀的编程能力:熟练使用 Python / C++ / CUDA / Go / Rust 中至少一门语言,具备良好的工程素养与代码风格 5.强烈的好奇心与自驱力:对 AI Infra / MLSys / LLM Serving / Agent System 方向充满热情,愿意深入底层解决系统级问题 6.良好的沟通协作能力:能清晰表达技术方案,与团队成员高效协同 加分项 1.推理框架经验:熟悉 SGlang、vLLM、TensorRT-LLM、DeepSpeed-Inference 等主流推理框架,有源码阅读或深度贡献(PR / Issue)经历 2.系统开发实习:在头部科技公司的 AI Infra、推理引擎、高性能计算或云原生团队有实习经验 3.Agent / RAG 系统经验:有 Agent、RAG、Multi-Agent 系统或 Function Calling 相关的开发与项目经验 4.云原生基础设施:熟悉 Kubernetes,了解 GPU 调度与容器编排 5.竞赛或科研经历:ACM/ICPC 等算法竞赛获奖,或在 MLSys / 系统 / AI 顶会(OSDI、SOSP、MLSys、NeurIPS、ICML、NSDI 等)有相关研究成果 6.开源影响力:有开源项目贡献或技术博客 / GitHub 活跃记录 为什么选择我们 站在 AI 系统的最前沿:你将直接参与大模型推理引擎和智能体平台的从 0 到 1 建设,接触 Disaggregated Serving、分布式 KV Cache、异构调度等行业最前沿的系统工程问题 真实的工程影响力:代码直接运行在大规模异构 GPU 生产集群上,你的每一次优化都在降低推理成本、加速整个公司的 AI 产品交付 全栈成长路径:从 GPU 算子到推理引擎到 Agent 运行时,你将获得横跨底层系…
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+
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
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/
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
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
Go+
https://www.youtube.com/watch?v=8uiZC0l4Ajw
学习Golang的完整教程!从开始到结束不到一个小时,包括如何在Go中构建API的完整演示。没有多余的内容,只有你需要知道的知识。
Rust+
https://www.youtube.com/watch?v=BpPEoZW5IiY
In this comprehensive Rust course for beginners, you will learn about the core concepts of the language and underlying mechanisms in theory.
https://www.youtube.com/watch?v=lzKeecy4OmQ
Full Rust 101 Crash Course for beginners.
https://www.youtube.com/watch?v=rQ_J9WH6CGk
AI agent+
https://www.ibm.com/think/ai-agents
Your one-stop resource for gaining in-depth knowledge and hands-on applications of AI agents.
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
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.
还有更多 •••
相关职位

校招算法序列
1、扎实的计算机/软件工程基础,对操作系统、设计模式等熟悉; 2、熟悉大数据相关计算、存储组件, 如 spark/flink/hbase/iceberg等; 3、熟悉云计算相关技术,如k8s/ranc
更新于 2026-08-10北京|上海|上海

校招算法序列
1、计算机、人工智能、数学、电子工程等相关专业硕士及以上学历; 2、具备大模型结构设计、训练优化或底层系统开发经验。 3、千卡集群实战经验: 具备千卡及以上规模 GPU/NPU等集群(如 B300
更新于 2026-08-10北京|上海|上海

校招算法序列
1、本科及以上学历,计算机、电子信息、自动化、车辆工程等相关专业 2、扎实的C/C++语言编程基础,良好的编程习惯 3、具有AEB、ADAS及自动驾驶开发经验者优先 4、具有较强的逻辑思维能力与解决问
更新于 2026-08-10北京|上海|上海