Robotics ML Research Scientist: Dexterous Manipulation

Deft Robotics; San Francisco (CA); On-site; USD 150,000 - 250,000; Full time

Benefits offered by this job

Medical, dental & vision plans

Daily meals stipend

Conference travel support

Job summary

Deft Robotics is seeking a skilled researcher/engineer to design and implement robot autonomy software stacks for grasping and dexterous manipulation in unstructured environments. You will explore state-of-the-art learning policies, including reinforcement and imitation learning, and deploy optimized, high-speed software for production use.

The role requires deep ML expertise, 3+ years of experience deploying ML systems, and strong experience with model lifecycle management.

Qualifications

• PhD or MS in Computer Science, Machine Learning, Robotics, or equivalent technical discipline.
• Deep expertise in machine learning fundamentals, reinforcement learning and associated frameworks (PyTorch, TensorFlow, Ray, etc.)
• 3+ years of proven track record developing and deploying ML systems from research through production implementation
• Hands-on experience with model lifecycle management including training, deployment, and maintenance in production settings.

Responsibilities

• Design and develop robot autonomy software stack and algorithms for grasping and dexterous behaviors.
• Research and implement state-of-the-art robot learning policies, including RL and imitation learning.
• Build high-speed autonomy software optimized for inference performance.
• Design and maintain data collection pipelines for production robot fleets.
• Optimize policies for distributed training and real-time edge deployment.
• Ship production quality, safety-critical software.

Skills

Machine learning fundamentals

Reinforcement learning

ML systems deployment

Education

PhD or MS in Computer Science, ML, Robotics

Tools

PyTorch

TensorFlow

Ray

Job description

Deft Robotics is seeking a skilled researcher/engineer to design and implement robot autonomy software stacks for grasping and dexterous manipulation in unstructured environments. You will explore state-of-the-art learning policies, including reinforcement and imitation learning, and deploy optimized, high-speed software for production use.

The role requires deep ML expertise, 3+ years of experience deploying ML systems, and strong experience with model lifecycle management.