Robot Learning Engineer — Dexterous Manipulation

Darwin Robotics; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Darwin Robotics is seeking a machine learning researcher or engineer to build autonomous robots that operate in the physical world. You will design and train models using Python, PyTorch, and NumPy, contributing to learning architectures, data collection, and evaluation on real robots.

You’ll work across learning, perception, and control, evaluating experiments and deploying policies with a small team. The role requires strong ML foundations and the ability to own research from data collection

Qualifications

• You are an exceptional machine learning researcher or engineer with strong foundations in deep learning.
• You have experience designing and training models.
• You think critically about architectures, learning algorithms, data, and experimental design.

Responsibilities

• Robot Learning Research: design, and train models and policies for learning complex physical tasks from demonstrations and experience.
• Dexterous Manipulation: develop learning approaches for precise manipulation, assembly, and tool use.
• Learning Architectures: design architectures for robot perception, reasoning, and control.
• Data & Training: design data collection strategies, training pipelines, and learning from real-world experience.
• Evaluation & Deployment: design experiments, evaluate performance, and improve policies on physical robots.

Skills

Deep learning

Model training

Experiment design

Tools

Python

PyTorch

NumPy

Job description

Darwin Robotics is seeking a machine learning researcher or engineer to build autonomous robots that operate in the physical world. You will design and train models using Python, PyTorch, and NumPy, contributing to learning architectures, data collection, and evaluation on real robots.

You’ll work across learning, perception, and control, evaluating experiments and deploying policies with a small team. The role requires strong ML foundations and the ability to own research from data collection