Research Engineer, Contrastive Learning

Key Skills

Java Programming, Python Programming, C++, C Programming, SQL, Cloud computing, Scala Programming, Machine learning techniques, Data science techniques, MATLAB Programming, PyTorch, TensorFlow, R Programming

Job Description

The AI & Biometrics team is building a biometric iris recognition system that can work reliably with more than a billion users and enables them to claim their free share of WLD. We use cutting-edge machine learning deployed on custom hardware to enable high-quality image acquisition, identification, and fraud prevention, all while requiring minimal user interaction. Our technology, coupled with privacy-preserving data collection, allows us to increase system performance and reduce model bias.

About the Opportunity:

This role is responsible for developing, building, and training deep neural networks that improve upon the current state-of-the-art in iris recognition. This involves translating the latest findings from various research groups worldwide into production where the system is continuously monitored and improved. This project includes cross collaboration with various teams—in particular the Data Infrastructure and Backend teams.

In this role you will:

• Develop deep neural networks to make iris recognition work on over one billion people.
• Monitor, maintain and improve the iris identification engine.
• Interact with our data collection team and design projects to collect the training data you need.
• Research state of the art computer vision technologies and adopt them to our use cases.

About You:

• Experience with computer vision and deep learning, ideally through past projects that have been deployed in production.
• Experience with contrastive learning, embedding learning, and self-supervised learning.
• Fluent in Python and deep learning libraries (e.g. Tensorflow/Pytorch).
• Well versed with the state-of-the-art in deep learning for computer vision.
• Ability to read and understand scientific papers, reproduce results, and transfer techniques to other domains.
• Bonus: Experience in setting up large training pipelines in a distributed training environment.
• Bonus: Experience interacting with MongoDB, PostgreSQL, and AWS.