Machine Learning / Computer Vision Engineer

What you'll do

• Build visual representation and perception pipelines for robotic manipulation, and develop visual models for reinforcement learning and imitation learning policies.
• Improve training data pipelines using domain randomization, synthetic data, rendering, sensor noise modeling, and real-world fine-tuning.
• Evaluate vision models and policies on real robotic tasks, diagnose failures, and collaborate on perception strategy and sensor evaluation.

What they ask for

• Ph.D. in computer vision or 3+ years of experience working on a computer vision product.
• Strong machine learning for computer vision background, especially deep learning-based visual perception.
• Experience training modern computer vision models in Jax, PyTorch or similar frameworks.
• Practical experience with visual representation learning or computer vision tasks such as detection, segmentation, pose, depth, tracking, or 3D perception; strong Python skills.

Nice to have

• Experience with visual policy training, domain randomization, synthetic data, rendering, or photorealistic simulation.
• Experience with robotics simulators, robot learning, real robot deployment, or first-author publications in listed venues.

Tools

Jax, PyTorch, Python, Isaac Sim, MuJoCo, ROS/ROS2

AI focus

Builds computer vision and visual representation learning systems for robotic manipulation, including models supporting reinforcement learning, imitation learning, and end-to-end visuomotor policies.