🛠 Tech Stack

💼 About This Role

You'll expand scene transformer models to generate multiple ego-vehicle trajectories in ambiguous cases and explore recursive multi-step losses for longer horizon predictions. Your work will directly impact safe autonomous truck deployment.

🎯 What You'll Do

• Modify scene transformer for multimodal ego trajectory generation
• Formulate recursive and multi-step loss functions
• Mitigate mode collapse for diverse feasible paths
• Design metrics for trajectory diversity and safety

📋 Requirements

• Expertise in trajectory prediction and behavior forecasting
• Experience training large-scale models with self-supervision
• Practical experience with PyTorch, Lightning, or JAX
• Understanding of AV stack components: localization, perception, planning

✨ Nice to Have

• Experience with uncertainty estimation (aleatoric, epistemic)
• Experience with multi-modal prediction and probabilistic modeling

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3Hiring Manager Interview· 45 min