Robot learning engineer

Company Description

We are an early-stage robotics startup working on building multi-purpose mobile robots that can do complex manipulation tasks. We are looking for a creative, skilled, and motivated robot learning engineers to join our team in advancing robot manipulation capabilities. We are looking for people with proven expertise in machine learning and/or robotics. You will collaborate with a team of talented researchers and engineers, and drive ongoing innovation and technological advancements within the company. This is a full-time on-site role in Santa Clara, CA.

Responsibilities

• Design and implement state-of-the-art learning algorithms for robot manipulation, navigation, and control—from simulation to deployment on physical systems

• Develop novel approaches to enhance robot dexterity and mobility using reinforcement learning, imitation learning, and foundation models, etc.

• Scale ML systems for large-scale model training and fine-tuning.

• Build diverse, robust manipulation skills that push the boundaries of what robots can do

• Collaborate closely with hardware, controls, and systems engineers to create integrated solutions

Qualifications

• PhD in Robotics, Computer Science, Electrical Engineering, Mechanical Engineering, or related field; OR Master's degree with 1+ years industry experience; OR Bachelor's degree with 3+ years industry experience

• 2+ years of hands-on experience developing AI systems for robotics applications

• Deep expertise in modern robot learning techniques (reinforcement learning, imitation learning, behavior cloning, etc.)

• Strong proficiency in Python and deep learning frameworks (PyTorch, TensorFlow, or JAX)

• Proven experience conducting real robot experiments and debugging complex robotic systems

• Experience with robot simulators (Isaac Gym, Isaac Sim, MuJoCo, SAPIEN, Drake, or similar)

• Excellent problem-solving abilities and strong communication skills

• Genuine passion for robotics and building products that work in the real world

Preferred Qualifications

• Publications at top robotics/ML conferences (RSS, CoRL, ICRA, IROS, NeurIPS, ICLR, etc.)

• Experience with vision-language models or foundation models for robotics

• Familiarity with sim-to-real transfer techniques and domain randomization

• Experience with distributed training and MLOps infrastructure

• Background in manipulation, grasping, or mobile manipulation

• Track record of taking research from prototype to production