Machine Learning Engineer - Senior
Full-timeDevelop and deploy machine learning models, with a focus on deep learning, reinforcement learning, and simulation-to-reality (sim2real) transfer for real-world robotics and control systems.
Cyberwave's vision is to unlock the full potential of intelligent machines by making robotics as accessible, scalable, and programmable as cloud software. We believe in a future where deploying robotic systems is no longer limited by complexity, fragmentation, or vendor lock-in.
Our mission is to accelerate this future through an AI-powered robotics platform that abstracts away hardware complexity and empowers developers to build, deploy, and scale robotic applications with high-level, intuitive commands. By bridging classical robotics frameworks (like ROS and ROS 2) with modern machine learning in a modular architecture, Cyberwave simplifies integration across heterogeneous systems. With built-in web-based simulation and digital twin tools, we enable seamless development, real-time monitoring, and faster iteration from concept to deployment—both in simulation and the real world.
We are building an A+ team with talent based in Zurich, Milan, and Rome. Join our dynamic and collaborative environment—whether from our Zurich headquarters or remotely within a similar time zone. Enjoy the flexibility to shape your own schedule while staying aligned with our shared goals and fast-paced mission.
We are seeking a highly skilled and motivated Machine Learning Engineer to join our AI team. This role involves developing and deploying machine learning models, with a focus on deep learning, reinforcement learning, and simulation-to-reality (sim2real) transfer for real-world robotics and control systems. You'll work closely with software, robotics, and hardware teams to build intelligent systems that learn in simulation and perform in the real world.
Requirements
- Degree in Computer Science, Robotics, AI, or a related field (BSc/MSc/PhD), with a strong foundation in applied mathematics, control theory, or computational modeling
- 3+ years of hands-on experience developing and deploying machine learning and deep learning models using frameworks such as PyTorch, TensorFlow, or JAX
- Demonstrated expertise in reinforcement learning, including implementation of algorithms like PPO, SAC, or DDPG in both simulated and real-world environments
- Deep understanding of sim-to-real techniques, including domain randomization, domain adaptation, transfer learning, and policy robustness across environments
- Practical experience with physics-based simulators (e.g., MuJoCo, Isaac Sim, PyBullet) and hands-on work with robotic hardware or embedded platforms
- Fluent in Python, with strong software engineering practices; working knowledge of C++ is essential for performance-critical systems
- Strong grasp of data-driven modeling, system identification, control strategies, and optimization methods relevant to robotic learning and deployment
Responsibilities
- Develop deep learning and reinforcement learning policies for perception, control, and decision-making (e.g., visuomotor policies, MPC-guided RL, goal-conditioned policies)
- Design and optimize cutting-edge ML/DL models for real-world robotics, tackling high-dimensional, dynamic, and noisy environments
- Develop advanced reinforcement learning agents in simulated environments such as MuJoCo, Isaac Lab/Sim, PyBullet, or proprietary simulators—pushing the boundaries of what machines can learn
- Lead sim2real transfer efforts, leveraging domain randomization, adaptation, and robust policy learning to ensure models generalize from virtual to physical systems
- Deploy end-to-end ML pipelines integrated with robotics or embedded systems, enabling real-time perception, decision-making, and control
- Collaborate across disciplines—working closely with simulation, hardware, and software teams to solve complex, system-level challenges
- Drive rapid experimentation, analyzing results, debugging performance bottlenecks, and continuously refining models for optimal real-world performance
- Build robust and scalable ML infrastructure, supporting automated training, evaluation, and deployment workflows across diverse robotic platforms