Robotics ML Engineer (m/f/d) Dexterous Manipulation

Agile Robots SE; München; Vor Ort; EUR 65.000 - 85.000; Vollzeit

Zusammenfassung

An international high-tech company in Munich seeks a Robotics ML Engineer to work on learning-based manipulation solutions. You will develop and stabilize manipulation policies, collaborate with experts, and leverage multiple sensory techniques for robot control. The ideal candidate has strong experience in robotics and deep learning, with solid programming skills in Python and C++. This role offers a collaborative environment and numerous development opportunities within a diverse team.

Leistungen

Corporate Benefits Program with 100€ net per month

Modern office with rooftop terrace

Development opportunities and company events

Qualifikationen

• Strong background in robotics with hands‑on experience applying machine learning.
• Solid understanding of imitation learning and reinforcement learning for robotic systems.
• Experience working with contact dynamics, compliance, and tactile feedback.
• Practical experience with robotic simulation and sim-to-real workflows.
• Strong programming skills in Python and C++.
• Ability to reason about system-level failures.

Aufgaben

• Develop and stabilize learning-based manipulation policies.
• Build learning pipelines combining various sensory signals.
• Develop ML-driven approaches for precise manipulation.
• Train and validate policies across simulation and real robots.
• Analyze tactile feedback to improve performance.
• Collaborate with robotics, perception, and ML teams.

Kenntnisse

Robotics & Deep Learning

IL / RL Experience

Embodiment & Control

Simulation & Deployment

Programming in Python and C++

System Debugging

Tools

ROS2

Jobbeschreibung

Robotics ML Engineer (m/f/d) Dexterous Manipulation

Join Agile Robots SE as a Robotics ML Engineer focused on learning-based, contact-rich manipulation. You will work at the intersection of learned policies and physical reality, using tactile sensing, force interaction, and precise control to ground robot intelligence.

Responsibilities

• Policy Grounding: Develop, refine, and stabilize learning-based manipulation policies under real-world contact, force, and compliance constraints.
• Multimodal Learning: Build learning pipelines combining high-resolution vision, tactile, and force-torque signals.
• Learning-Based Control: Develop and refine ML-driven approaches for precise, contact-rich manipulation.
• Sim-to-Real Deployment: Train, validate, and deploy manipulation policies across simulation and real robot hardware, addressing sim-to-real gaps.
• Debugging & Stability: Analyze tactile feedback, compliance behavior, and policy stability to improve performance.
• Cross-Functional Collaboration: Work closely with robotics, perception, and ML colleagues to prototype, iterate, and scale manipulation solutions.

Essential Skills

• Robotics & Deep Learning: Strong background in robotics with hands‑on experience applying machine learning to manipulation and control problems.
• IL / RL Experience: Solid understanding of imitation learning and reinforcement learning for robotic systems.
• Embodiment & Control: Experience working with contact dynamics, compliance, force interaction, or tactile feedback in real systems.
• Simulation & Deployment: Practical experience with robotic simulation and sim-to-real workflows, including deployment on physical robots.
• Programming: Strong Python and C++ skills, with experience using modern ML frameworks and ROS2-based systems.
• System Debugging: Ability to reason about system-level failures across perception, policy, control, and hardware.

Beneficial Skills

• Tactile/Haptic Systems: Experience with tactile sensing or force-feedback setups.
• Policy Post-Training: Exposure to policy refinement, fine-tuning, or robustness improvements under real-world constraints.
• Infrastructure & Deployment: Familiarity with containerization, model serving, or CI/CD pipelines for ML systems.
• Research Exposure: Publications or applied research experience in robotics, machine learning, or related fields.

What We Offer

• Dynamic high-tech company combined with financial soundness and world class investors.
• Interdisciplinary international team with 60+ 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 with rooftop terrace overlooking Munich, free drinks & fruits, and regular company events.

About Us

Agile Robots SE is an international high‑tech company based in Munich, Germany with a production site in Kaufbeuren and more than 2300 employees worldwide. Our mission is to bridge the gap between artificial intelligence and robotics by developing systems that combine state‑of‑the‑art force‑moment‑sensing and world‑leading image‑processing technology. This unique combination of technologies allows us to provide user‑friendly and affordable robotic solutions that enable intelligent precision assembly.

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