(Senior) AI Engineer (m/f/d) Embodied AI & Learning from Egocentric Videos

The AI Research Division of Agile Robots is looking for a (Senior) AI Engineer (m/f/d) Embodied AI & Learning from Egocentric Videos, who will develop learning algorithms that enable robots to acquire manipulation skills from large-scale egocentric video and multimodal demonstration data.

Your Responsibilities

• Learning Algorithms: Develop and improve AI algorithms for robot learning from egocentric video, using approaches such as Vision‑Language‑Action (VLA) models, world models, transformer‑based architectures, and foundation models.
• Data Pipelines: Design and implement scalable pipelines for egocentric data collection, synchronization, annotation, and preprocessing.
• Training Pipelines: Build large‑scale training and evaluation pipelines for robot learning from demonstrations.
• Multi‑Modal Learning: Explore learning approaches that combine video, audio, text, and sensory data.
• System Translation: Translate product and research requirements into scalable software architectures and production‑ready AI systems.
• Background: Master's degree in computer science, automation, robotics, AI, or a related field, or an equivalent combination of formal training and professional experience.
• Learning Architectures: Experience with one or more of Vision‑Language‑Action (VLA) models, world models, transformer‑based video models, diffusion models, or multimodal foundation models.
• ML Engineering: Proficiency in Python and deep learning frameworks such as PyTorch for AI development.
• Video Data Handling: Experience working with large‑scale video datasets, including preprocessing and annotation tooling.
• Robotics Software: Familiarity with ROS2 and software development for robotics.

Beneficial Skills

• Professional Experience: 2 to 5+ years of professional experience in robotics software engineering.
• Additional Languages: Familiarity with C++ alongside core Python proficiency.
• Robotic Integration: Hands‑on experience integrating perception, manipulation, or teleoperation on real robotic platforms.
• Publications: Publication record in machine learning, computer vision, or robotics venues.

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 facilities with a rooftop terrace overlooking Munich, free drinks & fruits, and regular company events contribute to a good working environment.

We are proud of our diversity and welcome your application regardless of gender and sexual identity, nationality, ethnicity, religion, age, or disability.