Senior/Staff Machine Learning Engineer, Motion Planning

Job description

Job responsibilities

• Develop state-of-the-art machine learning models for autonomous vehicle planning using rich map, perception, routing, and contextual sensor data.
• Design and implement model architectures for trajectory generation, behavior planning, and decision making that balance accuracy, robustness, interpretability, and runtime efficiency.
• Own the end-to-end machine learning lifecycle, including data curation, feature engineering, experimentation, training, evaluation, deployment, monitoring, and continuous improvement.
• Design rigorous offline evaluation methodologies, validation pipelines, and metrics to measure planning quality, safety, robustness, and generalization.
• Analyze model behavior, investigate failure cases, and improve performance through systematic error analysis and targeted experimentation.
• Collaborate closely with runtime, perception, prediction, mapping, and systems teams to deploy scalable machine learning solutions into production.
• Design validation strategies and rule-based guardrails to ensure generated trajectories are feasible, safe, and compliant with traffic rules.
• Stay current with advances in machine learning, robotics, and autonomous driving, translating research innovations into production systems.

Job requirements

• BS, MS, or PhD in Computer Science, Robotics, Machine Learning, or a related field.
• 4+ years of experience developing machine learning systems for robotics, autonomous driving, or other real-time decision-making systems.
• Strong Python programming skills and experience with modern deep learning frameworks such as PyTorch.
• Strong understanding of deep learning, sequence modeling, transformers, diffusion models, or other modern ML architectures.
• Experience designing datasets, experiments, validation methodologies, and metric-driven model evaluation.
• Strong software engineering skills with experience developing and maintaining production-quality software.
• Excellent debugging and analytical problem-solving skills, with the ability to investigate complex issues across datasets, model behavior, and production systems.
• Experience analyzing edge cases, tracing failures to their root cause, and improving model robustness through systematic experimentation.