Apply

Ready to go for it?

AI Apply speeds things up—apply directly if you prefer.

FREE ACCESS
5,000–10,000 jobs/day
Scoutfield Logo

See all jobs on Scoutfield

Search thousands of fresh jobs every day.

Discover
  • Fresh listings
  • Fast filters
  • No subscription required
Create a free account and start exploring right away.
Caterpillar Inc.

Autonomy End-to-End Development Engineer

Caterpillar Inc.

. 研究端到端自动驾驶模型(Sensor-to-Planning),打通感知、预测、决策全链路 .

Posted 11/4/2026full-timeWuxi • ChinaMid-LevelSeniorWebsite

Core Competencies

Role fit
Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in end-to-end autonomous driving models, including sensor-to-planning integration and visual-language-action frameworks. Proficient in deep learning, machine learning, and relevant programming languages, with a strong focus on algorithm development and implementation.

Highest-signal resume keywords
Deep LearningMachine LearningEnd-To-End Autonomous DrivingPyTorchTensorFlow

ATS Keywords

Tailor your resume
Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills
Deep LearningMachine LearningSequence ModelingTransformer ArchitectureEnd-To-End Autonomous Driving SolutionsVisual-Language-Action FrameworksPythonC++Imitation LearningDiffusion Policy
Soft Skills
Strong Research AbilityTechnical Sharing
Tools & Technologies
PyTorchTensorFlowROSROS2
Industry Keywords
Autonomous DrivingVisual-Language-ActionClosed-Loop Simulation TrainingRobotics ManipulationAlgorithm Prototyping

Tech Stack

Tools & technologies
PythonPyTorchTensorflowC++

About the role

Key responsibilities & impact
  • 研究端到端自动驾驶模型(Sensor-to-Planning),打通感知、预测、决策全链路
  • 探索由原始传感器数据直接输出规划轨迹的技术路线
  • 研究视觉-语言-动作(VLA)与机器人基础模型
  • 探索大语言模型/视觉语言模型作为推理引擎,处理矿区复杂工况下的语义理解与推理
  • 结合模仿学习、Diffusion Policy 等方法,研究装载、挖掘、卸载等作业技能学习
  • 推动作业级自主能力落地
  • 探索闭环仿真训练方法,提升模型在长尾工况下的泛化能力
  • 跟踪学术界与工业界前沿方案,完成算法原型搭建与验证
  • 定期开展技术分享,推动方案持续演进
  • 与感知、规划、控制及系统集成团队协同对接,输出算法方案与研究文档

Requirements

What you’ll need
  • 博士学历,计算机、人工智能、自动化、电子信息等相关专业
  • 具备扎实的深度学习与机器学习基础
  • 熟悉序列建模与 Transformer 架构
  • 熟练使用 PyTorch / TensorFlow
  • 熟悉经典端到端自动驾驶方案(如 UniAD、VAD)
  • 了解主流 VLA 架构(如 RT-2、OpenVLA)及 BEV / Occupancy 表征
  • 熟练使用 Python 和 C++
  • 具备良好的编码与工程实现习惯
  • 有端到端驾驶、VLA 或模仿学习相关的项目、竞赛或研究经历
  • 对前沿技术有浓厚兴趣和较强钻研能力
  • 加分项(非强要求):在端到端驾驶、VLA、模仿学习或 Diffusion Policy 方向有高水平论文或知名开源项目
  • 加分项(非强要求):了解世界模型、闭环仿真训练或强化学习
  • 加分项(非强要求):有机器人操作(manipulation)相关研究经历
  • 加分项(非强要求):熟悉 ROS / ROS2 与实车调试

Benefits

Comp & perks
  • Equal Opportunity Employer
  • Qualified applicants of any age are encouraged to apply
  • Opportunity to join a global team focused on creating stronger, more sustainable communities