ML Engineer, II - End to End (E2E)

Experience applying machine learning techniques such as computer vision, imitation learning, or reinforcement learning, to robotics, autonomous systems, or complex control environments.

Strong programming skills in Python and PyTorch, with experience writing production-quality ML code.

Experience training and evaluating machine learning models using large datasets and scalable compute environments.

Understanding of ML architectures used in End-to-End systems, such as BEV models, Transformers, VLA, or diffusion models.

Experience debugging model behavior, analyzing performance metrics, and iterating on training pipelines.

Ability to collaborate with cross-functional teams to integrate ML models into larger software systems.

Develop and train machine learning models for End-to-End percetion and planning, including approaches such as imitation learning and reinforcement learning.

Implement production-quality ML code to support model training, evaluation, and inference within the autonomy stack.

Analyze model performance, identify failure modes, and propose improvements to increase robustness and generalization across scenarios.

Contribute to model training pipelines and data workflows, curating datasets from simulation, fleet logs, and on-vehicle data.

Collaborate with simulation, validation, and autonomy engineering teams to test and evaluate End-to-End models across diverse driving environments.

Help integrate End-to-End models into simulation and testing workflows, enabling faster iteration and more comprehensive validation.

As a Machine Learning Engineer II – End-to-End, you will help develop and deploy End-to-End models that power both perception and decision-making for autonomous trucks. Working closely with teams across perception, prediction, planning, and safety, you will contribute to End-to-End models that enable safe, efficient, and human-like driving in real-world freight operations.

This role focuses on building, validating, and improving machine learning models and infrastructure that support End-to-End systems within the autonomy stack.