About the role
RoboService seeks a Senior ML Engineer to bridge remote-controlled hardware and autonomous robots on the factory floor. You will establish training pipelines, from teleoperation data collection to fine-tuning VLA models, and apply reinforcement learning to improve manipulation and locomotion tasks.
You will use high-fidelity simulators to validate agents before deploying to real hardware. Required is 3–5+ years in robotics or embodied AI, strong Python and DL framework skills, and experience
Fine-tune VLA models (open source and partner models). Manage Data Pipeline and Teleoperation/Imitation Learning activities for data quality. Oversee large datasets required for fine-tuning models. Apply RL techniques to fine-tune robot actions for robust production-line performance. Use high-fidelity simulators (Isaac Sim, Omniverse) to train and test agents before deployment. Collaborate with hardware teams to bridge software and hardware integration. MS or PhD in Robotics, CS, AI, or related field. 3–5+ years hands-on experience in robotics, deep learning, or embodied AI. Strong proficiency in Python and deep learning frameworks (PyTorch, TensorFlow, or JAX). Experience with Transformers and VLA architectures is highly desirable. Robotics Middleware: familiarity with ROS2 (Robot Operating System). Simulation: experience with physics-based simulators (NVIDIA Isaac Sim, Gazebo, MuJoCo). Data Engineering: manage high-quality demonstration datasets, automate data cleaning, and train pipelines. C++ experience is desirable. Proficiency in English; basic German a plus. Berlin office in downtown Relocation assistance Access to cutting-edge tech Impact on real manufacturing Startup environment Team of experts