About the role
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 Singapore 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: AlignerrType: Hourly ContractLocation: RemoteCommitment: 10–40 hours/week What You'll Do Design, develop, and iterate on MuJoCo simulation environments for robotics research and AI trainingImplement and tune reinforcement learning algorithms (PPO, SAC, TD3, etc.) to train agents in simulated tasksDefine reward functions, observation spaces, and action spaces that produce robust, transferable policiesDebug and optimize physics simulations — contact models, actuator dynamics, and scene configurationsEvaluate trained policies for stability, generalization, and sim-to-real transfer potentialDocument environment specifications, training procedures, and experimental results clearly and thoroughlyCollaborate asynchronously with research teams to align simulation work with broader project goalsStay current with the latest advances in robot learning, simulation, and embodied AI Who You Are Strong hands-on experience with MuJoCo (or MuJoCo via dmcontrol, Gymnasium/Gymnasium-Robotics, or similar wrappers)Solid understanding of reinforcement learning theory and practical training pipelinesProficient in Python and comfortable with ML frameworks such as PyTorch or JAXExperienced in defining and shaping reward functions for complex robotic tasksFamiliar with robot kinematics, dynamics, and control fundamentalsAble to read and write MJCF/XML model files and understand their physics implicationsSelf-directed, detail-oriented, and comfortable working independently in an async environmentStrong 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 GenesisBackground in multi-agent environments or hierarchical RLPublished research or open-source contributions in robotics, RL, or embodied AIExperience with imitation learning, model-based RL, or world modelsGraduate-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 labsFully remote and flexible — work when and where it suits youFreelance autonomy with the structure of meaningful, milestone-driven workDirectly influence how AI agents learn to interact with the physical worldEngage with a global community of top-tier ML and robotics practitionersPotential for ongoing work and contract extension as new projects launch