Role overview
The world is in a waste crisis. Currently we produce 2.1 billion tons of solid waste per year. Data collection of the waste we produce is non-existent, meaning no systematic transparency and no accountability. It means that recycling targets are not upheld, dumping of waste into our oceans remains nobody's responsibility, recyclables get sent to landfill or incineration, and producers get away with sub-standard packaging. Thus, recycling rates stubbornly remain at 10% and, unless we change, by 2040 the plastic stock in the ocean will have quadrupled - a problem that already costs society $1.5 trillion each year.
Our mission is to increase transparency and automation in waste management to accelerate the circular economy. Currently, our camera system and AI software are deployed in recycling plants and waste facilities around the world to measure material flows and provide waste analytics. We have compiled a team of experts to deploy our technology and we’re looking to expand our team.
What you'll work on
- Pushing the boundaries of deep learning by building upon the latest research in object detection and classification.
- Developing deep learning methods using best software development practices; training, analyzing, and reporting model performance.
Developing internal tools to further automate research and analysis workflows.
3+ years (5+ preferred) applying deep learning in industry settings.
Experience with applying latest Deep Learning research in PyTorch
Experience with active learning, semi-supervised learning, learning from noisy labels, model robustness (at least two)
Experience with architectures such as YOLO, ViT, ResNet
Ability to write clear, efficient, and scalable code using Python and PyTorch
Experience with numpy, scipy, OpenCV, Albumentations
Analytical detail-oriented mindset with strong abstract thinking and a solid theoretical understanding of neural networks