🎓 Research Intern – Robot Learning - Imitation Learning, Foundation Models, RL (MS/PhD, 6–12 months)

About the role

Join our research team to work on learning-based control and perception for real-world robot manipulation. You'll train and evaluate manipulation policies, build the data and evaluation infrastructure behind them, and run experiments that go all the way from an idea to a robot doing something new. We care more about your ability to train models that work than about any particular robot, task, or sensor you've used before.

Requirements

• 01Currently enrolled in an MS or PhD program in Robotics, Computer Science, Machine Learning, or related field
• 02Strong foundation in training neural networks — you can take a model from idea to a working, debugged result
• 03Strong foundation in imitation learning or reinforcement learning
• 04Proficiency in Python and at least one deep learning framework (PyTorch, JAX)
• 05Experience with vision-based policy learning — diffusion policies, 3D policies, vision-language-action models, video action models
• 06(+) Experience with robot simulators (e.g., MuJoCo, Isaac Gym/Lab)
• 07(+) Hands-on experience with robot hardware, real-world data collection, or sim2real adaptation
• 08(+) Familiarity with contact-rich or dexterous manipulation, or tactile sensing
• 09(+) Publications or preprints at robotics or ML venues (CoRL, RSS, ICRA, NeurIPS, ICML, ICLR)

Details & responsibilities

• 01Design, train, and evaluate manipulation policies on real hardware
• 02Run focused research experiments end-to-end — form a hypothesis, build the ablation, and draw a clear conclusion from noisy real-world results
• 03Integrate multimodal sensor streams (RGB, depth, proprioception, tactile) into policy architectures
• 04Contribute to data collection tools and replay infrastructure for learning from human demonstrations
• 05Work closely with hardware, AI, and perception engineers to close the loop from sensing to control

Compensation & benefits

• 01Paid internship with competitive compensation
• 02Work on cutting-edge problems in robot learning and manipulation
• 03Mentorship from researchers and engineers working at the frontier of embodied intelligence
• 04Access to real robot hardware and large-scale robot datasets
• 05Opportunity to publish or contribute to high-impact research alongside product-driven development