Software Engineer - Manipulation

What you'll do

• Develop, evaluate, and deploy manipulation policies for real-world tasks and hardware.
• Build post-training data pipelines and adapt policies using methods such as RL fine-tuning, distillation, and imitation learning.
• Transfer policies from simulation and offline evaluation to robots; define performance metrics and regression tests.

What they ask for

• Strong experience in robotic manipulation, including grasping, in-hand or whole-arm control, and high-DOF motion, with hardware deployment.
• Hands-on experience training and debugging learned policies, including post-training methods such as RL fine-tuning, distillation, and imitation learning.
• Proficiency in Python, C++, and PyTorch or JAX, and experience building real-time robotic software stacks.
• Experience with demonstration and teleoperation data and evaluation pipelines for learned policies.

Nice to have

• Experience with physics engines such as IsaacSim, MuJoCo, or Drake.
• Experience with generalist manipulation policies, VR/haptic teleoperation, tactile sensing, or computer vision.

Pay

$180,000 - $240,000 USD base salary

Tools

Python, C++, PyTorch, JAX, IsaacSim, MuJoCo, Drake

AI focus

Develop and post-train learning-based robotic manipulation policies, including RL fine-tuning, policy distillation, and interactive imitation learning, and deploy them on physical robots.