(Senior) Robotics AI Engineer (m/w/d) Video & Multimodal Data

About The Role

The AI Team at Agile Robots is looking for a dedicated (Senior) Robotics AI Engineer (m/w/d) Video & Multimodal Data with strong expertise in computer vision and machine learning, with a particular focus on robotic understanding. You are expected to have 2 to 5 years of experience in the field, showing proficiency in working with large-scale video datasets in the context of robotic learning. This position is at the intersection of AI and robotics, with a focus on enabling robots to learn effectively from video demonstrations and observations. Prior hands-on experience in these areas would be a significant plus. 

Your Responsibilities

• AI Methods: Develop and improve deep learning, VLA-based, or transformer-based approaches for video learning in robotics.
• Synthetic Data: Design and implement synthetic robotic videos for large-scale training data generation.
• Multimodality: Explore learning approaches that leverage video, audio, and sensory data.
• Integration: Collaborate with robotics engineers to embed video-based learning methods into robotic systems.
• Architecture: Translate functional and technical requirements into detailed system architecture and design.

Essential Skills

• Education: Master’s degree in Computer Science, Robotics, AI, Automation, or a related field. 
• Computer Vision: Strong background in video understanding, action recognition, or video-based imitation learning. 
• Deep Learning: Proficiency in methods and frameworks (e.g., PyTorch, TensorFlow), ideally in video or multimodal contexts. 
• Datasets: Experience with large-scale video datasets, including preprocessing, annotation, and pipeline design. 
• Programming: Familiarity with Python, software development practices and robotics frameworks (e.g., ROS2). 
• Soft Skills: Excellent problem-solving abilities, collaborative mindset, and strong communication skills.

Beneficial Skills

• Advanced Models: Experience with transformer-based video models, diffusion models, or multimodal architectures.
• Motion Retargeting: Knowledge of motion retargeting methods in robotics.
• Model Deployment: Experience with serving frameworks such as TorchServe or TensorFlow Extended.
• DevOps: Familiarity with containerization (Docker) and CI/CD pipelines.
• Publications: Track record of scientific publications in leading venues in ML, Computer Vision, or Robotics.

What We Offer

• Dynamic high-tech company combined with financial soundness and world class investors.
• Join an interdisciplinary, international team with 60+ different nationalities in a collaborative work environment.
• Lots of development opportunities in the context of our continued growth.
• Challenging tasks and impactful projects alongside experts that enable professional and personal growth.
• Corporate Benefits Program that covers health, mobility and learning with 100 € net per month.
• Modern office facilites with a rooftop terrace overlooking Munich, free drinks & fruits, and regular company events contribute to a good working environment.