端到端规控算法科学家

Company Description Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology - with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch. Job Description • 研发面向自动驾驶的端到端规划与控制算法，重点包括从传感器输入直接进行轨迹规划、运动控制与驾驶策略学习。 • 设计并优化集成感知、预测、规控模块的端到端一体化框架，实现实时车辆决策。 • 开发适用于复杂城市场景的轨迹优化、路径生成与控制策略，包括路口、拥堵及动态环境。 • 与感知、预测团队协作，构建下一代端到端自动驾驶系统，确保模块间无缝衔接。 • 与全球博世团队合作，进行端到端规控研究的技术转移、趋势追踪与方案评估。 Research and develop end-to-end planning and control algorithms for autonomous driving, focusing on trajectory planning, motion control, and driving policy learning directly from sensor inputs. Design and optimize integrated E2E frameworks that unify perception, prediction, and planning/control modules for real-time vehicle decision-making. Develop trajectory optimization, path generation, and control strategies for complex urban scenarios, including intersections, congestion, and dynamic environments. Collaborate with perception and prediction teams to build state-of-the-art E2E autonomous driving systems and ensure seamless module integration. Work with global Bosch units on technology transfer, trend scouting, and concept evaluation for E2E planning and control research. Qualifications • 计算机科学、电气工程、机器人或相关专业的硕士或博士学位。 • 拥有1-3年在自动驾驶或AI应用领域担任规控算法开发的实践经验，聚焦规划、控制或端到端驾驶。 • 精通轨迹预测、运动规划、控制理论与优化方法（如MPC、数值优化、强化学习、模仿学习）。 • 具备端到端驾驶模型、规控一体化或行为克隆的实践经验（真实环境或仿真）。 • 熟练掌握Python及PyTorch或TensorFlow等深度学习框架。 • 熟悉CARLA、nuPlan或其他自动驾驶仿真平台者优先。 • 在顶级会议（如CVPR、ICCV、ECCV、NeurIPS、ICRA、CoRL）以第一作者身份发表论文者优先。 • 加分项：在量产项目中负责轨迹规划、运动控制或端到端驾驶策略的经验。 • 英语流利，具备强大的沟通和团队合作能力。 • Master’s or PhD in Computer Science, Electrical Engineering, Robotics, or a related field. • 1-3 years of practical experience in algorithm development for autonomous driving or AI applications, with focus on planning, control, or end-to-end driving. • Strong knowledge of motion planning, control theory, and optimization methods (e.g., MPC, numerical optimization, reinforcement learning, imitation learning). • Hands-on experience with E2E driving models, planning-control integration, or behavioral cloning in real-world or simulation environments. • Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow. • Experience with CARLA, nuPlan, or other autonomous driving simulation platforms is a strong plus. • First-author publication at top conferences (e.g., CVPR, ICCV, ECCV, NeurIPS, ICRA, CoRL) is a strong plus. • Bonus: Experience with tasks such as trajectory planning, motion control, or end-to-end driving policy in mass-production projects. • Fluent in English, with strong communication and teamwork skills.