Senior/Staff Machine Learning Research Scientist, Robustness and Uncertainty

Who We Are 

Nuro exists to better everyday life through robotics. The company’s custom electric autonomous vehicles are designed to bring the things you need—from produce to prescriptions—right to your home. Nuro’s autonomous, goods-focused solution can give you valuable time back and more freedom to do what you love. This convenient, eco-friendly alternative to driving has the potential to make streets safer and cities more livable. 

About the Role

The mandate of the learned behavior team is to use advanced machine learning techniques to accelerate software progress. In this role, you will work closely with the software vertical teams to understand their pain points and explore novel and advanced machine learning methods to solve practical real-world challenging problems. To name a few, using self-supervised learning to learn robust representations, exploring techniques for out-of-distribution detection to solve long tail problems, adjusting reinforcement learning techniques for motion generation and selection, working on trajectory prediction and motion planning, investigating the robustness of models to mitigate uncertainties, or trying to build an end-to-end driving system. If you love solving challenging new problems with a mindset of deriving practical solutions to eventually be used on the vehicle, come join us!

About the Work

• Detect anomalies and out-of-distribution examples
• Investigate the adversarial inputs to Autonomy modules and ways to be robust against them
• Mitigate the uncertainties accumulated through the Autonomy stack
• Work on goal-based, conditional, and joint trajectory prediction and motion planning
• Research new machine learning problems and models
• Collaborate with autonomy teams to understand their pain points and priorities to define milestones of the corresponding roadmaps
• Derive practical solutions and deploy them on the NuroBot and for the Nuro DriverTM

About You

You have deep expertise and prior experience in some or many of the following areas:

• You have an M.Sc. or Ph.D. (preferable) focusing on one or more of the following areas: Computer Science, Artificial Intelligence, Mathematics, or a closely related field
• You have subject matter expertise and research in one or more of the following areas: Machine Learning, Deep Learning, Statistics, Probability theory, Robustness theory, Robotics, or Autonomous Driving (preferable)
• Deep knowledge of ML Robustness and experience in how to use it in practice to improve the ML models' generalization
• Theoretical and practical aspects of Certified Robustness
• Experience in handling and estimation of Uncertainty for ML Models 
• Background in mining Adversarial/OOD/Anomaly Examples 
• Understanding the pros and cons of Adversarial Training
• You have strong problem-solving and programming skills in C++ or Python
• Strong culture fit and good team player
• Demonstrated research publications in any of the major conferences (RSS, ICRA, CoRL, CVPR, ICLR, ICML, NeurIPS, ICCV, AAAI, etc.)

At Nuro, your base pay is one part of your total compensation package. For this position, the reasonably expected base pay range is between $202,350.00 and $303,050.00 for the level at which this job has been scoped. Your base pay will depend on several factors, including your experience, qualifications, education, location, and skills. In the event that you are considered for a different level, a higher or lower pay range would apply. This position is also eligible for an annual performance bonus, equity, and a competitive benefits package.

At Nuro, we celebrate differences and are committed to a diverse workplace that fosters inclusion and psychological safety for all employees. Nuro is proud to be an equal opportunity employer and expressly prohibits any form of workplace discrimination based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, veteran status, or any other legally protected characteristics.