Key Skills

Job Description

About The Role What if your expertise in robotics and machine learning could directly shape how the next generation of intelligent agents learn to move, manipulate, and interact with the physical world? We're looking for Robotics ML Experts in the Netherlands with hands-on MuJoCo experience to design, build, and refine simulation environments that train AI systems to perform real-world tasks — from locomotion and dexterous manipulation to complex multi-agent coordination. This is a fully remote, flexible contract role for experienced practitioners who live and breathe physics simulation, reinforcement learning, and robot control. If you've spent time wrangling MJCF files, tuning reward functions, and debugging contact dynamics, this role was made for you. Organization: Alignerr Type: Hourly Contract Location: Remote Commitment: 10–40 hours/week What You'll Do Design, develop, and iterate on MuJoCo simulation environments for robotics research and AI training Implement and tune reinforcement learning algorithms (PPO, SAC, TD3, etc.) to train agents in simulated tasks Define reward functions, observation spaces, and action spaces that produce robust, transferable policies Debug and optimize physics simulations — contact models, actuator dynamics, and scene configurations Evaluate trained policies for stability, generalization, and sim-to-real transfer potential Document environment specifications, training procedures, and experimental results clearly and thoroughly Collaborate asynchronously with research teams to align simulation work with broader project goals Stay current with the latest advances in robot learning, simulation, and embodied AI Who You Are Strong hands-on experience with MuJoCo (or MuJoCo via dm_control, Gymnasium/Gymnasium-Robotics, or similar wrappers) Solid understanding of reinforcement learning theory and practical training pipelines Proficient in Python and comfortable with ML frameworks such as PyTorch or JAX Experienced in defining and shaping reward functions for complex robotic tasks Familiar with robot kinematics, dynamics, and control fundamentals Able to read and write MJCF/XML model files and understand their physics implications Self-directed, detail-oriented, and comfortable working independently in an async environment Strong written communicator who can document technical work clearly Nice to Have Experience with sim-to-real transfer techniques (domain randomization, system identification) Familiarity with other physics simulators — Isaac Gym, PyBullet, Drake, or Genesis Background in multi-agent environments or hierarchical RL Published research or open-source contributions in robotics, RL, or embodied AI Experience with imitation learning, model-based RL, or world models Graduate-level coursework or degree in robotics, ML, computer science, or a related field Why Join Us Work on cutting-edge robotics and AI simulation projects alongside leading research labs Fully remote and flexible — work when and where it suits you Freelance autonomy with the structure of meaningful, milestone-driven work Directly influence how AI agents learn to interact with the physical world Engage with a global community of top-tier ML and robotics practitioners Potential for ongoing work and contract extension as new projects launch

Core Responsibilities

Design, develop, and optimize MuJoCo simulation environments to train AI agents for complex robotic tasks. Implement reinforcement learning algorithms and collaborate with research teams to ensure robust policy performance and sim-to-real transfer.

Requirements

Requires strong hands-on experience with MuJoCo, reinforcement learning theory, and proficiency in Python with ML frameworks like PyTorch or JAX. Candidates should be comfortable working independently and possess a solid understanding of robot kinematics and dynamics.

Benefits

• Fully remote work
• Flexible schedule
• Freelance autonomy
• Meaningful milestone-driven work