We are seeking a robotic controls researcher to work with a collaborative team within Meta’s Reality Lab Research. This team is leveraging recent advances in robot embodiments, tools for data collection, and modern control policies, to advance robotic dexterous manipulation. The chosen candidate will work with a highly interdisciplinary team of researchers, engineers, and designers, and will have access to advanced technology, resources, and testing facilities.
Responsibilities
- Conducting collaborative research on developing control algorithms for a wide range of robotics platforms
- Development of model predictive control approaches mapping robot observations and target references to low-level actuation control signals
- Development of robotic data collection sets and evaluations
Minimum Qualifications
- Bachelor's degree in Mechanical Engineering, Electrical Engineering, Control Systems Engineering, Computer Science, or in a relevant technical field, or equivalent practical experience
- Experience with both traditional reflexive controllers (PID, LQR, OSC) and modern predictive controllers (MPCs)
- Experience with generative AI models such as transformers, LLMs, VLMs, VLAs, and diffusion models
- A track record of research contributions with your work published in top conferences and journals such as Robotics (RSS, ICRA, IROS, CoRL, T-RO, IJRR), Machine Learning (NeurIPS, ICML, ICLR, AAAI, JMLR), and Computer Vision (CVPR, ICCV, ECCV, TPAMI) Ph.D. in Mechanical Engineering, Electrical Engineering, Control Systems Engineering, Computer Science, or relevant degree and 5+ years experience in robotic control systems
- 2+ years experience with both traditional reflexive controllers (PID, LQR, OSC) and modern predictive controllers (MPCs)
- Experience with physical systems, including interfacing with novel sensors and actuators
- Experience working with robot manipulation
- Experience with robotic data collection for training autonomous control policy models