9 months ago
Responsibilities
- Design and implement scalable ML training pipelines for computer vision models.
- Build efficient model serving infrastructure for real-time inference on edge devices.
- Optimize models for deployment on embedded hardware.
- Develop continuous training and evaluation systems to improve model performance.
- Create data pipelines for managing multi-modal sensor datasets.
- Implement model monitoring and performance analytics for deployed systems.
- Collaborate with researchers to transition models from research to production.
- Build tools for distributed training and experiment tracking.
Requirements
- Strong experience with ML frameworks like PyTorch and TensorFlow.
- Deep understanding of computer vision architectures and deployment tradeoffs.
- Hands-on experience deploying models on edge devices.
- Expertise in building MLOps infrastructure and CI/CD for ML.
- Experience with distributed training frameworks and GPU cluster management.
- Strong software engineering skills in Python and systems languages like C++ or Rust.
- Familiarity with video processing and multi-modal perception systems is a plus.
- Prior experience in robotics or real-time ML applications is highly valued.