(Senior) ML Research Engineer (m/f/d) Robotics

About the role:
The AI Research Division of Agile Robots is looking for ML engineers with strong experience in robotics-adjacent domains such as (simulation research, generative modelling, or multimodal ML) and who can build machine-learning systems end-to-end, not just train models. You don’t need a robotics background, but you do need solid engineering instincts, clean Python, and the ability to work with complex, noisy, real-world data.

This posting serves as a broader entry point to our teams. After we evaluate your background, we’ll match you with the specific role and team where your skills have the most impact. The team assignment happens during the interview process.

Your Responsibilities:
• Model development: Build ML components across perception, prediction, or policy pathways (e.g., video models, multimodal encoders, world models, diffusion/transformer architectures).
• Systems integration: Work with real datasets, real-time constraints, and ML pipelines that must operate reliably on embodied robotic platforms.
• Multimodal data: Work with inputs such as video, teleoperation actions, proprioception, tactile signals, or simulation-generated sequences.
• Evaluation & iteration: Test models in realistic environments, analyze failure modes, and refine for stability, drift, latency, and robustness.
• Cross-disciplinary collaboration: Partner with teams focusing on modelling, robotics, teleoperation, simulation, and data systems; depending on the final role you land in.

Essential Skills:
• Deep ML experience in video modelling, generative models, sequence modelling, world models, RL, or simulation-based learning.
• Strong software engineering ability: writing clean, modular Python and building ML systems end-to-end; including implementing architectures, training loops, and data pipelines from scratch.
• Real-world ML mindset: experience with noisy, multimodal, temporal, or large-scale datasets (not just clean academic examples).
• Engineering maturity: ability to debug, profile, optimize, and scale ML systems beyond prototype level.
• PyTorch expertise: hands-on experience with training pipelines, distributed workloads, or deployment workflows.

Beneficial Skills:
• Multimodal intuition: combining signals such as vision, pose, audio, force/tactile, or simulation state.
• Systems sense: familiarity with streaming architectures, real-time constraints, microservices, or serialization formats (e.g., Protobuf / MCAP).
• Embodied-AI curiosity: interest in teleoperation interfaces, robot interaction, or real-world control dynamics.
• Simulation experience: knowledge of Isaac Sim, MuJoCo, Unity, Unreal, or related simulation platforms.

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.