MERL is looking for a self-motivated and qualified candidate to work on modeling for contact phenomenon. Robotic manipulation is heavily affected by external contacts that can be modeled with physical and data driven models. We are interested in researching those models for analysis and control purposes. The ideal candidate is a PhD student and should have experience and records in multiple of the following areas. Contact modeling and robotic manipulation. Physic Engines like Mujoco, Bullet, Drake and sim2real gap problems. Machine learning techniques for modeling and control such as Gaussian Processes and Neural Networks. Experience in working with robotic systems. Knowledge in learning from demonstration algorithms and standard Reinforcement Learning algorithms is a plus. Proficiency in Python is required. The successful candidate will be expected to develop, in collaboration with MERL employees, state of the art algorithms that will lead to a scientific publication. Typical internship length is 3-4 months.

MERL is seeking a highly motivated and qualified intern to join the Signal Processing Group for a three month internship program. The ideal candidate will be expected to carry out research on collaborative learning between infrastructure, devices, and vehicles. The candidate is expected to develop distributed learning for various applications, including autonomous driving, smart infrastructure, mobile networks, etc.. The candidate should have knowledge of federated learning and distributed computing, networking and over-the-air-computation. Knowledge of scheduling, spectrum management, and mathematical analysis for convergence testing is a plus. Candidates in their junior or senior years of a Ph.D. program are encouraged to apply.

MERL is looking for a self-motivated intern to work on problems at the intersection of video understanding and graph representation learning for solving few-shot action recognition problems. The ideal candidate would be a PhD student with a strong mathematical background in machine learning and computer vision and who has published at least one paper in a top-tier machine learning or computer vision venue (NIPS/CVPR/ECCV/ICCV/ICML/PAMI etc.). The candidate must have prior experience in using deep learning methods for video understanding (such as using Transformers) and self/unsupervised methods (such as contrastive learning). Proficiency in PyTorch is expected and familiarity with neural language models will be a plus. The intern will conduct original research with MERL researchers towards scientific publications. This internship requires work that can only be done at MERL.