Back to jobsJob overview
About the role
Research Scientist Intern, Multimodal Learning for Robotics (PhD) at Meta
Required Skills
pythonpytorchcomputer visionroboticsmachine learningmultimodal learningtactile sensingmujoco
About the Role
Research Scientist Intern focused on developing computer vision and tactile algorithms for robotic control in dextrous manipulation tasks. The role involves collaborative research at the intersection of robotics, machine learning, and human-robot interaction within Meta's Reality Labs Research.Key Responsibilities
- Conduct collaborative research on developing CV and tactile based algorithms for human and robotics data
- Develop robotic data pipelines for robotic dextrous manipulation
- Train models and benchmark different algorithms
- Collaborate with researchers and cross-functional partners
- Communicate research plans, progress, and results
Required Skills & Qualifications
Must Have:
- Currently has or is in the process of obtaining a Ph.D. in Computer Science, AI, Robotics, or related field
- Experience in computer vision with contributions in 3D reconstruction, hand pose estimation, or object pose estimation
- Understanding of state-of-the-art robotic manipulation control policies
- Experience with Python, PyTorch, JAX, or related languages
- Must obtain work authorization in country of employment
Nice to Have:
- Proven track record with publications at leading robotics, ML, or CV conferences
- Experience with multimodal learning including tactile data
- Experience working with robot manipulation
- Experience building pipelines with foundation CV models like CLIP, DinoV2, or SAM2
- Experience working and communicating cross-functionally in teams