Research Engineer, Post-training & Deployment

Job description

Job responsibilities

• Research, post-train and evaluate large deep learning models for robotic manipulation tasks.
• Develop frameworks to continuously improve robot behaviors.
• Collaborate closely with our product teams to source and iterate on customer requirements to ensure technical alignment for on-site deployments.
• Own scenario setup and data collection methodologies, managing the operational lifecycle for unique customer use-cases.
• Work with our robotics teams to maintain and ensure robots are deployment-ready and execute full-stack software and hardware deployments at customer sites.
• Build robust testing and evaluation pipelines for tracking model improvements and corner cases.

Job requirements

• BS, MS or PhD degree in Computer Science, Robotics, Engineering or a related field, or equivalent practical experience.
• Proficiency in Python and at least one deep learning library such as PyTorch, TensorFlow, JAX, etc.
• Deep technical knowledge in computer vision and deep learning for robotics, including reinforcement and imitation learning.
• Prior experience working with large-scale model training.
• Prior experience developing and deploying ML models or software on real robots.
• Prior experience with ROS/ROS2 or other robotics middleware platforms.
• Bonus if you have experience working with customers and deploying real-world robotics applications.
• Bonus if you have experience leveraging LLMs to accelerate development and solve complex engineering problems.