ADAS Algorithm Engineer – Plan & Control Evaluation 智驾规控算法评测算法工程师

Tasks

• Evaluation Framework Development: Design, build, and maintain the foundational ADAS performance evaluation framework, including data preprocessing modules, task scheduling engines, and report generation components.
• Performance Evaluator Development: Develop scenario-specific Evaluator modules for L2, Active Safety, and NGA sub-scenarios. Develop rule-based Evaluators as a baseline, iterate with data-driven parameter tuning using collected field data, build reusable data-driven tooling, and ultimately deliver a module-based comprehensive Evaluator.
• Develop agents and skills that restructure evaluation development workflows and collaboration modes, boosting productivity and communication.
• Conduct Evaluation: Use Golden Sample management and replay pipelines for open-loop and closed-loop scenarios, covering data selection, version comparison, and regression validation.
• Reporting and Frontend Infrastructure: Develop task-triggering and result-visualization frontend systems for complex evaluation and analysis. Support automated generation of major release gate reports, minor version evaluation reports, and day-to-day operations.
• AI/Agent Toolchain: Leverage AI, Skills, and Agent technologies to transform development workflows and tooling, such as Scrum Master automation, enabling cross-functional teams to onboard quickly.
• Enablement for Non-Algorithm Teams: Based on AD stack code, develop Agent-powered tools for System Engineers and Validation teams, such as rapid debugging tools driven by test data. Provide SWE56 testing tools and bench support.

Qualifications

Education: Master’s degree in vehicle engineering, computer science, robotics, electrical engineering, automation, or a related field.

• 3+ years of experience in autonomous driving, ADAS, or robotics; ADAS/AD experience, especially planning algorithms, is preferred.
• Understanding of L2/L2+ functional scenarios and common evaluation metrics.
• Familiarity with data processing and analysis workflows, data-driven development, parameter tuning, or applied machine learning.
• Hands-on experience with an AD stack module, such as BEV perception, learning-based planning, or end-to-end models, is a plus.
• Daily active user of AI coding assistants such as Cursor, Claude Code, or GitHub Copilot, with experience building or orchestrating AI Agent workflows for real business tasks.
• Strong cross-team collaboration and communication skills, including the ability to work with suppliers and internal stakeholders.
• Familiarity with C++ and Python programming, ROS programming, and related tools.
• Willingness to share knowledge, self-motivation, and the ability to influence and lead a team with a positive, hardworking, and optimistic attitude.

Specific Knowledge

• Proficient in automotive electronics industry systems, processes, standards, and toolchains.
• In-depth understanding of automotive product and technology development trends.
• Proficient knowledge of Plan and Control algorithms and AD software development processes.
• Good understanding of ADAS function design, overall vehicle E/E architecture, and CP and AP AUTOSAR.
• Fluent English; German is a plus.

Benefits

• Events for employees
• Flextime
• Possible hybrid work
• Health benefits
• Mobility offers
• Employee discounts

Contact

Mercedes-Benz Group China Ltd., Xingchi Tower, No. 399, Keqiao Road, Jinqiao, Pudong, 201206 Shanghai. Recruitment China: recruitment_cn@mercedes-benz.com