🛠 Tech Stack

💼 About This Role

You'll conduct research on interpretable AI methods for end-to-end learned automated driving policies. Your work will develop glass-box representations to help debug and validate learned driving behaviors. This role bridges TRI research with Toyota products.

🎯 What You'll Do

• Conduct research on interpretable AI for end-to-end driving policies.
• Develop structured representations of driving behavior.
• Implement methods linking behavior to perceptual cues.
• Design experiments to assess interpretability and failure modes.

📋 Requirements

• Master's or PhD in Machine Learning, Robotics, or related field.
• Peer-reviewed publications at NeurIPS, ICML, ICLR, CVPR, CoRL, RSS, or ICRA.
• Python proficiency with deep learning frameworks.
• Experience with end-to-end learning for robotics or autonomous systems.

✨ Nice to Have

• Experience with interpretable AI or model introspection.
• Familiarity with structured/hybrid models (e.g., latent-variable models).
• Background in automated driving or safety-critical AI systems.

🎁 Benefits & Perks

• 🧪 Cutting-edge research environment at TRI.
• 💰 Competitive compensation and equity.
• 🩺 Health, dental, and vision insurance.
• 🏖️ Paid time off and holidays.
• 📚 Professional development opportunities.

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite Interview· 4 hours