Robotic AI Engineer/Applied Scientist - Foundation Models
Maven Robotics2 months ago
Responsibilities
- Architect model architectures for ultra-high task success rates with minimal human demonstrations.
- Develop novel co-training strategies and efficient learning algorithms using diverse data sources.
- Build models capable of zero-shot or few-shot adaptation to new robot configurations.
- Formulate and deploy novel Reinforcement Learning methods for real-world manipulation.
- Collaborate on advanced data collection systems to capture critical human intervention data.
Requirements
- MS or PhD in CS, Robotics, Machine Learning, or a related field, or equivalent industry experience.
- Advanced understanding of transformers, multi-modal alignment, and motor control.
- Proven ability to innovate within areas like VLA models, Real-world RL, or large-scale Data Infrastructure.
- Expert-level proficiency in Python and familiarity with PyTorch or JAX.
Benefits
- Work on a unique in-house robot platform that evolves alongside your models.
- Contribute to architectural breakthroughs aimed at achieving 99.9% task success rates.