Senior Software Engineer - Core-Simulator: Simulation Vehicles

Aurora hires talented people with diverse backgrounds who are ready to help build a transportation ecosystem that will make our roads safer, get crucial goods where they need to go, and make mobility more efficient and accessible for all. We’re searching for a Senior Software Engineer - Core-Simulator: Simulation Vehicles.

The team is responsible for the primary simulation engine and offline testing framework. They build models for subsystems of the autonomy stack, models for the physical world, and tooling to generate complex scenarios. They build the technology for producing realistic virtual interactions at scale, modeling the physics and behaviors of agents in the world, and gaining and presenting insights about our rich simulation data.The team's goal is to enable rapid development and validation of the autonomy stack through comprehensive offline analysis.

In this role, you will

• Improve the simulation fidelity of Aurora vehicle platforms by using techniques from system identification.
• Contribute to the V&V of Aurora vehicle platforms in simulation by leveraging statistical estimation theory and model validation methods.
• Improve vehicle dynamics and actuator models with application to off-nominal and failure-mode conditions.
• Design experiments (nominal and off-nominal) to collect sufficient data to improve model accuracy and parameter robustness.
• Contribute to the development of a scalable and robust vehicle simulation framework including large-scale simulation evaluation in order to assess performance across a wide range of environmental conditions including wind disturbances.
• Engage with numerous teams across the org including safety, controls, motion planning and external partners.
• Example projects that a candidate may contribute to include:
• Develop statistical model validation metrics to support V&V including: 
• Goodness of fit
• Parameter confidence intervals
• Model nonlinear actuation phenomena including vehicle brake hysteresis, backlash, amplitude and rate saturation, dead zones, etc. 
• Devise novel parameter estimation methods
• Improve computational performance of the vehicle simulation framework
• Contribute to the data collection effort including the design of optimal excitation maneuvers, data pre-processing, filtering, and time and frequency domain analysis.
• Investigate and troubleshoot discrepancies that are found between on-road and simulation data
• Contributing to modeling real world errors in, and testing closed-loop interactions between, perception, planning, localization, mapping, and control subsystems in simulation. 

Required Qualifications

• Must have strong experience with estimation theory including: 
• Least squares, Maximum Likelihood methods, and Kalman Filtering.
• Coefficient of determination, parameter confidence intervals, Hypothesis testing.
• Must have significant experience with system identification including strong understanding of foundational concepts such as
• Excitation
• Data collinearity
• Optimal input design
• Experimental/Data Collection pipelines
• Modeling of disturbances, parametric uncertainty, and unmodeled dynamics
• Real-time parameter estimation approaches
• Must have significant experience in physics-based modeling spanning a variety of applications.
• Must have experience in modeling and simulation of wind.  Experience sought includes:  ground vehicles, aircraft, rotorcraft, or wind energy systems.
• Must have experience with signal processing techniques
• Must have a Ph.D. degree in electrical engineering, robotics, aeronautics, mathematics, computer science, or similar technical fields of study, or equivalent practical experience
• 5+ years of industry experience programming C++ software or equivalent
• 15+ years of experience in physics-based modeling, simulation, robotics, motion planning, controls, or equivalent.

Desirable Qualifications

• Strong math background including: Lie groups (modern geometry) and stochastic processes
• Exposure to simulation fidelity requirements and standards
• Experience with SLAM (Simultaneous Localization and Mapping) and control (linear and nonlinear methods)
• Experience with automotive dynamics
• 5-10+ years of industry experience designing and programming C++ software
• Excellent communication and people engagement skills
• Experience with classical machine learning (ML) algorithms (backpropagation neural networks, support vector machines, ridge regression, etc)

The base salary range for this position is $168,000-$252,000 per year.  Aurora’s pay ranges are determined by role, level, and location. Within the range, the successful candidate’s starting base pay will be determined based on factors including job-related skills, experience, qualifications, relevant education or training, and market conditions. These ranges may be modified in the future. The successful candidate will also be eligible for an annual bonus, equity compensation, and benefits.

 #LI-KW1

#Mid-Senior