About the job

Your tasks

• 
  
• You develop and improve perception models for autonomous mobile robots, including object detection, obstacle classification, and free-space estimation
• 
  
• You drive data-centric machine learning by scaling automated labeling, leveraging fleet data, and closing the sim2real gap through synthetic data and simulation-based evaluation
• 
  
• You own model performance by defining benchmarks, tracking key metrics, and continuously improving real-world and benchmark results
• 
  
• You deploy and validate perception models within our ROS-based robot software stack, ensuring reliable performance on real vehicles
• 
  
• You collaborate closely with navigation, controls, and fleet software teams to deliver robust perception capabilities that enable autonomous operation
• 
  

Requirements

• 
  
• You bring 2–5 years of professional and hands-on experience in robotics perception, computer vision, or machine learning
• 
  
• You have strong Python skills; experience with C++ is a plus
• 
  
• You have hands-on experience training and evaluating neural networks (PyTorch or similar) and follow a data-centric approach to improving model performance
• 
  
• You have practical experience with synthetic data, simulation for ML, auto-labeling, active learning, or domain adaptation
• 
  
• You apply a rigorous approach to model evaluation and understand how to measure real-world performance effectively
• 
  
• You are familiar with ROS and Linux-based development environments
• 
  
• You have a pragmatic engineering mindset and enjoy shipping, measuring, and iterating