The objective of this position is to drive innovation in projects focused on the development and application of data analytics tools to support our engineering (e.g., ASU engineering) and operations (e.g., ASU, SMR, Electronics Carry Gas).
您将如何贡献和成长？
Focusing on the business needs of Air Liquide in the context of our customer-centric transformation, the researcher will be responsible to:
Collaborate with business entities to define the problem and business requirements, translate them into functional design specifications, and develop solutions. Identify, evaluate and select industrial or academic partners as needed.
Develop and optimize core algorithms for Embodied AI, including:
Multimodal Perception: Fuse sensory data from vision (cameras), LiDAR, and tactile sensors to enable robots to "see" and "comprehend" complex industrial settings.
Autonomous Planning & Decision-making: Research the application of AI models (e.g., LLMs/VLMs, Reinforcement Learning, world models) for high-level task planning, reasoning, and dynamic decision-making.
Learning & Control: Develop efficient robotic control policies, particularly through Reinforcement Learning (RL), Imitation Learning (IL), and Sim-to-Real transfer, allowing robots to rapidly acquire new skills (e.g., dexterous manipulation, obstacle-avoiding navigation).
Lead the end-to-end deployment of Embodied AI algorithms on industrial robots and mobile manipulators (AMR + robotic arms), overcoming the technical challenges of Sim-to-Real transfer in complex, real-world industrial environments.
Participate in the joint debugging of robotic hardware and software systems. Collaborate closely with internal engineering and process teams to drive the production/laboratory deployment of tasks such as smart grasping, autonomous navigation, and complex equipment manipulation.
Train team members on the details of the implemented methodology, thus ensuring sustainability of the solution for Air Liquide.
Support knowledge transfer within Air Liquide. Publish research in internal R&D reports, at conferences and potentially in peer-reviewed journals.
Maintain keen insights into advancements across Physical/Embodied AI, robotics, and LLM/VLM applications, strategically evaluating and introducing new technologies to drive technical choices and innovation.
您是合适的人选么？
Master’s degree or Ph.D. in Robotics, Computer Science, Artificial Intelligence, Automation, or a related engineering discipline. Proven experience in independent and interdisciplinary research is highly preferred.
Deep project experience in Computer Vision (CV) (e.g., object detection, segmentation) and Reinforcement Learning (RL).
Solid foundation in machine learning; expert proficiency in Python and at least one mainstream deep learning framework (PyTorch preferred).
Solid understanding of robot kinematics, dynamics, SLAM (mapping and localization), and path planning.
Proficiency in ROS (ROS/ROS2) with rich, hands-on development experience.
Proven track record of deploying and debugging algorithms on at least one type of physical robot (e.g., quadrupedal robots, UAVs, mobile robots/AGVs, or robotic arms).
Outstanding rapid-learning agility and the ability to navigate open-ended, ambiguous technical challenges.
Excellent communication and interpersonal skills (written and oral). Must be comfortable to work in English on a daily basis and in a multi-disciplinary and international team. Knowledge of French is of benefit.
