Machine Learning Engineer Intern (Planning)

Join our team as a Machine Learning Engineer Intern in the Planning department. In this role, you will work on expanding the scene transformer model to generate multiple trajectories for ego-vehicle in ambiguous scenarios. You will also explore longer horizon predictions using recursive and multi-step losses. This internship offers unlimited paid time off, flexible working arrangements, health benefits, equity options, professional development opportunities, and daily catered lunches.

• Expand the scene transformer model to provide multiple trajectories for ego in ambiguous cases and explore longer horizon predictions.
• Modify and expand an existing Scene Transformer framework to generate a diverse set of ego-vehicle trajectories for ambiguous scenarios.
• Formulate and experiment with recursive, autoregressive, and multi-step losses to stabilize long-horizon trajectory rollouts.
• Strong debugging, experiment design, data analysis, and failure-mode investigation skills
• Understanding of AV stack components: localization, perception, tracking, prediction, and planning
• Experience with uncertainty estimation (aleatoric, epistemic), multi-modal prediction, and probabilistic modeling
• Practical experience with PyTorch, PyTorch Lightning or JAX
• Expertise in trajectory prediction, behavior forecasting, and multi-agent motion modeling
• Experience training large-scale models with self-supervision, contrastive learning, representation learning, or scene-level modeling