- Design, train, and deploy production-grade deep learning models for depth estimation, segmentation, and tracking.
- Fine-tune models for real-time inference on embedded NVIDIA GPU platforms using quantization-aware training.
- Manage the end-to-end model development lifecycle from prototyping to deployment and validation.
- Collaborate with robotics teams to integrate perception outputs and architect onboard pipelines.
- Analyze performance data to identify failure cases and improve model robustness for outdoor conditions.
- Develop strategies for leveraging both real-world site data and synthetic data for model training.