Machine Learning Engineer (PAI)

at  iProov

Machine Learning Engineer
If you’d like to make the online world a safer place, come and join us.
About iProov
iProov is the world leader in face biometric verification. We are on a mission to make the Internet a safer place for businesses and consumers and work with fantastic customers across a number of industry sectors - organisations using our technology include the US Department of Homeland Security, the UK Home Office, the NHS, Eurostar, the Australian government, the Singapore government, UBS and many more.
Diversity at iProov is about reflecting the customers we serve, holding the principles of equality and inclusion at the heart of everything we do and all that we stand for, embracing differences, creating possibilities, and growing together. We aim to foster a culture where individuals of all backgrounds feel confident in bringing their whole selves to work, feel included and their talents are nurtured, empowering them to contribute fully to our purpose.
The Role
Reports to: Platform AI Team Lead
Location: London HQ - Hybrid (minimum once in the office per week)
Comp: Negotiable (Base) + iCompany Performance Bonus (Lvl 2) + Share Options + UK Proov Benefits
We are seeking an experienced Machine Learning Engineer to join our team and play a critical role in the research, development, and maintenance of advanced multi-modal deep learning systems. These systems are designed to detect a wide range of biometric attacks, including synthetic masks, deepfakes, and face-swaps, ensuring the security of millions of customers against identity fraud. The role involves implementing state-of-the-art research, writing high-quality code, and developing automated pipelines and tooling to update systems as needed.

• Research and Development: Conduct thorough research on the latest advancements in deep learning and biometric security. Implement and test new methodologies to improve attack detection capabilities.
• System Maintenance: Develop, maintain, and optimise deep learning models that are robust and scalable, ensuring high performance in real-world scenarios.
• Automation Pipelines: Create and manage automated pipelines that facilitate seamless updates and improvements to the detection systems, ensuring they remain up-to-date with the latest threats and techniques.
• Collaboration: Work closely with cross-functional teams, including machine learning researchers, software engineers, and product managers, to integrate new features and enhancements into the existing systems.
• Performance Analysis: Conduct initial and ongoing analysis of system performance, identifying areas for improvement and ensuring that security gaps are addressed promptly.