Hayden AI is looking to transform transit systems and other government agencies by leveraging computer vision to address real-world challenges such as bus lane and bus stop enforcement, and transportation optimization.
Requirements
- Deep Learning Frameworks: Expertise in PyTorch or TensorFlow (one mandatory, familiarity with both a plus).
- Computer Vision Libraries: OpenCV.
- Deployment Optimization Tools: TensorRT.
- Strong Python programming and software design with experience in Pandas.
- Experience deploying DL models to run on real-world, resource-constrained, systems with a pragmatic approach towards problem-solving.
- Demonstrated proficiency in data science and traditional machine learning (SVMs, Random Forests). Prior experience with automated machine learning pipelines is desirable.
- Automated data annotation for computer vision.
- Training multi-task and semi-supervised deep learning models for video data.
Responsibilities
- Oversee the entire perception system development life cycle, from problem definition to deployment and ongoing improvement.
- Lead a team of computer vision and perception engineers to develop and refine the system in a hands-on manner.
- Spearhead the development of robust computer vision algorithms for object detection, tracking, semantic segmentation, and classification.
- Champion the development and training of deep learning models for complex urban scene perception and real-time analysis.
- Collaborate with cross-functional teams (cloud/device) for seamless integration and monitoring of perception models.
- Analyze data to identify performance bottlenecks and opportunities for enhancing the perception system.
- Foster automation in the improvement cycles of deep learning models used within the perception system.
Other
- 2+ years leading and managing teams focused on developing real-world computer vision and perception systems using deep learning on edge devices.
- Communicate technical findings and insights effectively to stakeholders across the company to drive performance improvements.
- Utilize data visualization tools to present complex information clearly for informed decision-making.
- Familiarity with designing multi-modal deep learning models incorporating temporal context and geometrical constraints is a plus.
