- Waltham, Massachusetts, United States
- $177K–$225K per year
- 3+ years
Architect, train, and deploy large-scale behavior models for the Atlas humanoid robot, focusing on multimodal input and generalization across manipulation tasks.
Compensation
The base pay range for this position is between $177,000 to $225,000 annually.
Responsibilities
- Architect and train end-to-end VLA and Large Behavior Models for mobile manipulation on Atlas
- Build large-scale imitation learning pipelines that learn from human demonstrations, teleoperation, and simulation data
- Work on large pre-training across multiple data sources, and fine-tune for precision tasks
- Develop policies capable of few-shot generalization across diverse factory manipulation tasks
- Integrate your models into Atlas’s autonomy stack in collaboration with controls and platform teams
Requirements
- Master's in Machine Learning, Robotics, Computer Science
- PhD in Machine Learning, Robotics, Computer Science
- Nice to have: Deploying learned policies on real robots
- Nice to have: Curating large robotics datasets
- Nice to have: Reinforcement learning