小鹏汽车自动驾驶仿真评测工程师
社招全职自动驾驶板块地点:广州状态:招聘
任职要求
1. 计算机、物理等相关强理工类专业,熟悉Linux操作系统,掌握Python、C++至少一种编程语言; a. C++方向:具有扎实的C++编程功底,熟悉面向对象编程、标准库、泛型编程,掌握常见设计模式、了解性能优化、内存管理,具备良好的代码习惯; b. python方向:熟悉数据结构、函数与模块、异常处理等基础编程;掌握类与对象、继承与多态等面向对象编程;了解和能使用装饰器、生成器和迭代器等高级特性,熟悉os、sys、re、json、datetime等常用模块以及numpy、pandas、matplotlib、requests等常用库,具备良好的编程习惯; 2. 对自动驾驶有浓厚兴趣和强烈热情,掌握基本的自动驾驶软件/系统和模型相关的背景知识; 3. 认同小鹏汽车公司文化,有较强的自驱力和事业心,有把问题闭环关闭、独立创造价值的意识和能力。 4. 要求具备优秀的沟通力和理解力,能高效与软件/模型开发人员沟通协作,快速推动自动评测能力的迭代提升; 5. 严谨细致,逻辑能力强,有敏锐的问题排查和分析能力,能快速发现和解决问题。
工作职责
1. 【仿真运营】运营高级别自动驾驶系统的大下游(决策规划控制)及大上游(感知定位融合)的全链路仿真闭环测试流程,以及自动驾驶大模型仿真验证业务流程,快速形成简洁有效的测试报告,驱动研发解决长尾问题; 2. 【场景建设】理解自动驾驶业务和技术栈,对重点问题进行分析分类,建立和维护高级别自动驾驶corner case的场景数据库, 软件迭代过程中进行科学管理和更新汰换、保持场景库的高质量、高覆盖性和高有效性,有力支持研发快速验证模型和软件改动; 3. 【评估开发】理解自动驾驶和仿真技术栈,发现和总结各类问题的仿真评价规律,并转化成仿真评测的metric(c++程序),提升仿真评价的精准度和自动化;并针对模型仿真测试过程中产生的新的需求,快速完善metric,不断提升仿真测试KPI的准确性和完备性,提升仿真测试的价值贡献度。
包括英文材料
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
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
设计模式+
https://liaoxuefeng.com/books/java/design-patterns/index.html
设计模式,即Design Patterns,是指在软件设计中,被反复使用的一种代码设计经验。使用设计模式的目的是为了可重用代码,提高代码的可扩展性和可维护性。
[英文] Design Patterns
https://refactoring.guru/design-patterns
Design patterns are typical solutions to common problems in software design. Each pattern is like a blueprint that you can customize to solve a particular design problem in your code.
https://www.youtube.com/watch?v=NU_1StN5Tkk
Design Patterns tutorial explained in simple words using real-world examples.
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
JSON+
https://developer.mozilla.org/zh-CN/docs/Learn_web_development/Core/Scripting/JSON
用于将结构化数据表示为 JavaScript 对象的标准格式,通常用于在网站上表示和传输数据(例如从服务器向客户端发送一些数据,因此可以将其显示在网页上)。
NumPy+
https://numpy.org/doc/stable/user/absolute_beginners.html
NumPy (Numerical Python) is an open source Python library that’s widely used in science and engineering.
[英文] NumPy - Learn
https://numpy.org/learn/
Below is a curated collection of educational resources, both for self-learning and teaching others, developed by NumPy contributors and vetted by the community.
https://www.kaggle.com/code/themlphdstudent/learn-numpy-numpy-50-exercises-and-solution
This kernel uses exercises of NumPy from the Machine Learning Plus webpage
https://www.youtube.com/watch?v=KHoEbRH46Zk
If you've heard of Pandas and NumPy, you may think one is simply a superset of the other.
https://www.youtube.com/watch?v=QUT1VHiLmmI
Learn the basics of the NumPy library in this tutorial for beginners.
https://www.youtube.com/watch?v=VXU4LSAQDSc
This video serves as an introduction to the NumPy Python library.
Pandas+
[英文] 10 minutes to pandas
https://pandas.pydata.org/docs/user_guide/10min.html
This is a short introduction to pandas, geared mainly for new users.
[英文] Cookbook - pandas
https://pandas.pydata.org/docs/user_guide/cookbook.html#cookbook
This is a repository for short and sweet examples and links for useful pandas recipes.
https://www.kaggle.com/learn/pandas
Solve short hands-on challenges to perfect your data manipulation skills.
https://www.youtube.com/watch?v=2uvysYbKdjM
I'm super excited for this one. We're doing another complete Python Pandas tutorial walkthrough.
https://www.youtube.com/watch?v=Mdq1WWSdUtw
Filtering, Joins, Indexing, Data Cleaning, Visualizations
Matplotlib+
https://matplotlib.org/stable/tutorials/index.html
This page contains a few tutorials for using Matplotlib.
https://www.youtube.com/watch?v=c9vhHUGdav0
This video serves as an introduction to the Matplotlib Python library.
https://www.youtube.com/watch?v=OZOOLe2imFo
In this video we do a complete Matplotlib crash course in Python.
编程规范+
[英文] Google Style Guides
https://google.github.io/styleguide/
Every major open-source project has its own style guide: a set of conventions (sometimes arbitrary) about how to write code for that project. It is much easier to understand a large codebase when all the code in it is in a consistent style.
自动驾驶+
https://www.youtube.com/watch?v=_q4WUxgwDeg&list=PL05umP7R6ij321zzKXK6XCQXAaaYjQbzr
Lecture: Self-Driving Cars (Prof. Andreas Geiger, University of Tübingen)
https://www.youtube.com/watch?v=NkI9ia2cLhc&list=PLB0Tybl0UNfYoJE7ZwsBQoDIG4YN9ptyY
You will learn to make a self-driving car simulation by implementing every component one by one. I will teach you how to implement the car driving mechanics, how to define the environment, how to simulate some sensors, how to detect collisions and how to make the car control itself using a neural network.
相关职位

社招
一、 负责仿真场景库的搭建,包括场景库生成、管理维护、场景分类体系等,保障仿真测试的覆盖度。 负责对仿真中发现的自动驾驶算法问题进行分析,推动问题解决。 负责仿真评价体系的建设与测试方案设计,促进仿真测试覆盖度以及仿真路测一致性的提升。 负责仿真测试工具链的开发,提高仿真测试效率。 二、
更新于 2025-01-24

社招
1、建设和维护闭环仿真评价体系建设,针对不同场景不同问题进行数据挖掘 2、建设EndToEnd/子模型开环评测体系,提升评测效率,管理存量和增量真值数据系统 3、支持全产品全模式评测体系,量化评测标准,强化数据驱动占比 4、对自动驾驶模块功能,信息流动趋势有较深的理解 5、基于大数据基础框架实现Model Evaluate Model能力
更新于 2024-05-06
社招2年以上自动驾驶
1. 深入理解智能驾驶各模型算法,深度嵌入研发团队,设计评测方案、指标体系,回测策略等,并进行测试用例编写、评审、执行,分析指标变化和badcase,出具测试报告,持续跟进算法进展和问题验证; 2. 模型评测集方案构建,跟数据组配合采集、标注测试集; 3. 负责搭建算法测试环境和平台,编写自动化测试脚本; 4. 协助算法开发人员分析算法结果,抽象问题域; 5. 设计算法质量保证流程,推进算法指标迭代。