Algorithms Engineer

SeeTrue is a leader in modern computer vision and machine learning practices.

The Algorithms group is in charge of creating cutting edge algorithmic solutions aimed to automatically detect a wide variety of threats within X-ray and CT security scans. This solution will help the existing (manual) analysis/detection processes become faster and more accurate.

As a researcher on the team, you will get a chance to work alongside some of the best minds in the field and implement the latest machine learning and computer vision algorithms, in a multidisciplinary and dynamic environment.

Responsibilities: 

• Research, design and develop machine learning and computer vision based algorithms to detect a wide variety of threats within X-ray and CT security images
• Work with a multi-disciplinary team of security experts and engineers to deliver an end-to-end product: from the idea phase, through collecting and assessing the data, exploring algorithmic approaches, developing, testing, validating and integrating the algorithm in the production environment
• Read and implement algorithms publications in the field of machine learning and computer vision • Contribute to the team’s methodologies, best practices and toolset, share your work and give/receive feedback from peers in the team
• Showing strong understanding of software development and using it to translate Algo ideas into bullet-proof software

Qualifications: 

• M.Sc. in computer science or electrical engineering (preferably in the field of ML and CV) • 
• 10+ years of development of complex computer vision and/or machine learning models (ideally python based) • Great problem-solving skills, and drive for creativity and innovation
• Great achiever with obsessive drive to complete its missions excellently
• Strong communication and collaboration skills
• Team player, positive and driven, fast learner
• Hands on experience with deep learning using common frameworks (Keras, TensorFlow, etc.) – advantage •
• All candidates need to pass a security classification eligibility