Robotics Engineer - Embodied AI

Robotics Engineer - Embodied AI

About the Role We are building in-house humanoid robotics capabilities that enable robots to perceive, reason, and act autonomously for real-world service and operational applications. This position is for a hands-on Embodied AI Engineer with experience in robot learning, responsible for developing, fine-tuning, deploying, and validating intelligent behaviors on physical humanoid robots. The role offers broad ownership across AI development, data collection, robot integration, testing, failure analysis, and continuous performance improvement. The ideal candidate is comfortable working across disciplines and taking ideas from early experimentation through to real-robot deployment in a start-up style environment.

Key Responsibilities - Develop, integrate, and fine-tune robot foundation models for perception, mapping, task planning, and embodied decision-making. - Own the development cycle from data collection and model training to physical-robot deployment and validation. - Test and analyse system failures, then improve performance through targeted data collection, model retraining, and iterative validation in both simulation and real-world environments. - Track key performance metrics, including task success rate, completion time, intervention rate, repeatability, and safety.

Minimum Requirements - Good knowledge of VLA models, imitation learning, reinforcement learning, or diffusion policies. - Master’s degree or above in Robotics, Computer Science, AI, Engineering, or a related field. - Willingness to work across AI, robotics, hardware, data collection, testing, and operations. - Hands-on experience with robotic systems, including integration, calibration, or teleoperation.

Strongly Preferred - Hands-on experience deploying and validating AI models on physical robots is a major advantage. - Proven experience deploying learned policies on real robotic systems, including humanoid, bimanual, dexterous, or contact-rich manipulation. - Experience across data collection, model training, deployment, and real-robot validation. - Experience training and fine-tuning large robot-learning models using cloud-based GPU infrastructure. - Demonstrable hands-on work through deployed systems, projects, publications, or robot demonstration videos.

What We Offer - The opportunity to work directly on embodied AI models and deploy them on physical humanoid robots. - A hands-on role combining research, model development, system integration, and real-world deployment. - The chance to see your work move beyond simulation and operate in real environments.

Work Type - Full-time | On-site