This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
We’re searching for a Software Engineer II to join the Control Simulation team and help transform how we validate and improve the safety and performance of the Aurora Driver. In this role, you will operate at the intersection of Machine Learning, Software Engineering, Data Science, and Vehicle Dynamics. You will contribute to the development of our next-generation data driven vehicle simulator, build data pipelines that source critical scenarios from our fleet and generate simulations from logs, and analyze data to prove the safety of our motion control software. This is a high-impact role for an engineer who enjoys a mix of model development, infrastructure building, and data analysis.
Job Responsibility:
Develop Vehicle Models: Help design and implement our next-generation differentiable vehicle dynamics simulator for controls V&V
Build Simulation Pipelines: Design and maintain the software pipelines required to generate "Sim-from-Log" scenarios. You will ensure that high-value on-road events are systematically converted into reproducible simulation tests
Implement Control Scenario Taxonomies & Curate Data: Build the data structures and algorithms to categorize complex control scenarios (e.g., maneuvers, environments) and use this framework to source balanced datasets from on-road logs, ensuring comprehensive ODD coverage for model training
Requirements:
BS or MS in Computer Science, Robotics, Data Science, or a related engineering field
2+ years of software engineering experience with a focus on data-intensive applications or machine learning
Strong proficiency in Python (including libraries like Pandas, NumPy, Scikit-learn)
Hands-on experience with PyTorch or similar machine learning frameworks
Experience working with large datasets, SQL, and data processing pipelines
Strong analytical skills with the ability to translate complex data into actionable engineering insights
Nice to have:
Background or interest in Control Theory or Vehicle Dynamics (understanding of kinematics, kinetics, and actuation)
Experience with machine learning or system identification for physics based-models
Familiarity with V&V methodologies, simulation frameworks, or log analysis tools
Experience building data visualization tools or dashboards to track software quality and coverage
Proficiency in C++ (necessary for integrating with on-vehicle or production codebases)