Senior Machine Learning Engineer, Computer Vision

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:

Our project demands that our biometric device (the Orb) provides a good user experience and is able to capture high quality biometric data. Our gimballed imaging system that captures the iris from various camera positions is essential for gathering quality data. This role is responsible for development and maintenance of the software that controls the imaging system. This involves the development of computer vision models, their integration on the hardware device, and collecting additional data for the continual improvement of our model’s performance.

In this role you will:

• Interact with the hardware, orb firmware, and data collection teams to design workflows for collecting the training data you need.
• Build custom data labeling services to increase the quality of our training data.
• Setup and train neural networks to solve tasks like localization or semantic segmentation.
• Design techniques to analyze the performance of your engines, find weaknesses, and improve them (e.g. through data augmentation).
• Ensure that the biometric engine performs equally well across different demographics.
• Implement visualization tools and monitoring systems for tracking imaging performance, data drift and edge case robustness
• Setup experiments and do research on iris recognition in general (e.g., measure reaction times of the pupil contraction).

About You:

• Industry experience or PhD in computer vision applications with deep learning, ideally through past projects that have been deployed in production.
• Good understanding of image processing and analysis methods such as edge detection, registration, image quality measures, denoising and image fusion.
• Have an eye for detail in regards to data and label quality.
• Fluent in Python and deep learning libraries (e.g. Pytorch/Tensorflow)
• 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: Familiarity with Rust as well as experience interacting with MongoDB, PostgreSQL, and AWS.