
Position now closed
SAIS is recruiting a research associate in the security of ML-based personal assistants
Please note: this position is no longer being recruited for.
Full-time, fixed term to start ASAP until 30 November 2023 at the South Kensington Campus.
The successful candidate will join the UKRI-funded project “Secure AI Assistants”, jointly run by King’s College London and Imperial College London. The overarching aim of the project is to develop various methods to assess the security of personal AI assistants, including identifying unwanted aspects of the system so that they can be rectified.
The role will focus on specification and verification methods for AI assistants based on machine-learning. This will involve both the development of off-line verification methods, and methods for online monitoring when training happens at runtime during user interaction. Familiarity with existing methods for verification of neural networks, e.g., MILP-based methods, SAT-based methods, abstraction, and optimisation is highly desirable, but candidates demonstrating an ability and willingness to become familiar with these topics and able to contribute to them will also be considered. Working knowledge of neural networks, including recurrent networks such as LSTM and related ML methods would also be an advantage.
William Seymour RECRUITMENT
recruitment