Machine Learning Engineer – Motion Planning & Prediction

Job description

Job responsibilities

• Design, train, and deploy models for behavioral prediction and motion planning that run on vehicles in real traffic
• Model multi-agent interaction and temporal dynamics — how a merge, an unprotected left, or an occluded pedestrian actually unfolds
• Own the metrics: build evaluation frameworks that correlate with real on-road safety and performance, not just offline loss
• Diagnose long-tail failures from real driving logs and close the loop back into training data and model design
• Optimize trained models for real-time inference under strict latency, memory, and compute constraints on embedded hardware
• Build and maintain data pipelines that process, clean, and label large-scale vehicle sensor and simulation datasets

Job requirements

• Hands-on experience with at least one of: behavioral or trajectory prediction, motion planning, decision-making under uncertainty, or closely adjacent autonomy work (navigation, SLAM, control, or…
• Experience deploying machine learning to real hardware operating in the physical world , under real-time or resource constraints. Simulation-only or offline-only experience does not meet this bar.