Job Description

Salary: Not Specified Location Type: Not Specified Employment Type: Not Specified

Position Overview

Latitude AI (lat.ai) is developing automated driving technologies, including L3, for Ford vehicles at scale. We are dedicated to reimagining the driving experience to make travel safer, less stressful, and more enjoyable for everyone. As a Ford Motor Company subsidiary, we operate independently to develop automated driving technology at the speed of a technology startup.

Company Information

Latitude is headquartered in Pittsburgh with engineering centers in Dearborn, Mich., and Palo Alto, Calif. When you join the Latitude team, you will collaborate with leading experts across machine learning and robotics, cloud platforms, mapping, sensors and compute systems, test operations, systems and safety engineering.

Meet the Team: Virtual Test Ecosystem (VTE)

The VTE team is responsible for implementing the tooling used by Latitude for simulations and resimulations. This includes:

• Simulations: Pure virtual scenarios where interactions are controlled and permutations are swept via a descriptive scenario language.
• Resimulations: Rerunning logs collected on-vehicle using an updated version of the autonomy stack.

This work involves backend C++ simulation/resimulation frameworks that call underlying autonomy tasks and Python-based tooling for large-scale cloud execution. This infrastructure significantly reduces autonomy developer iteration time and enables large-scale safety testing before code is deployed on vehicles.

The VTE team works closely and iteratively with autonomy teams to build new sim/resim features for evaluating their new autonomy features. We also collaborate with offboard testing teams to ensure they can use our tooling to write tests efficiently. Continuous benchmarking and evaluation of application efficiency and scalability are key to reducing runtimes and costs.

Responsibilities

• Add new features to the core C++ simulation/resimulation framework based on needs from autonomy and testing teams. This may involve simulating complex interactions with other actors, map features, new portions of the autonomy stack, or intentionally introducing degradations to test downstream component reactions.
• Collaborate directly with autonomy and testing teams to understand their needs and pain points, and propose infrastructure improvements or simulation realism enhancements.
• Provide support for user troubleshooting and bug fixes.
• Analyze simulation/resimulation reproducibility and develop tooling to identify the root cause of non-determinism in autonomy tasks or simulation/resimulation code.
• Gain in-depth knowledge of the autonomy stack to effectively integrate new autonomy features, perform initial root-causing of crashes or issues, and act as a bridge between the VTE team and autonomy teams.

Requirements

• Expertise in modern C++ (C++17).
• Self-driven to write efficient, well-tested, well-documented code that conforms to the style guide.
• 3+ years of experience developing software for autonomous vehicles.
• 1+ years of experience developing software for a simulation environment.
• Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, Robotics, or a related field, plus 4+ years of relevant experience.