Sunday, March 26, 2023
HomeUK JobResearch Assistant/Associate in Verification of Neuro-symbolic Learning

Research Assistant/Associate in Verification of Neuro-symbolic Learning

Spread the love

The Department of Computing at Imperial College London is a leading department of computer science, with a strong international presence in verification and artificial intelligence.

We are seeking to hire an outstanding Research Assistant/Associate to join the Verification of Autonomous Systems (VAS) group, led by Prof. Alessio Lomuscio.

The successful candidate will have a background in either machine learning, verification, or optimisation, and will join the HorizonEurope project “EVENFLOW”. The overarching aim of the project concerns the development of neuro-symbolic methods for learning and verification in the context of event prediction, including the prediction of critical events or states in highly-distributed and uncertain environments. Previous knowledge of event-based systems, or monitoring, particularly in high-performance settings will be advantageous to the successful candidate. Aspects of explainability, safety and reliability will also be pursued within the project.

The role will focus on application and development of methods for the verification of feed-forward neural networks, as well as neuro-symbolic structures accounting for temporal dependencies, suitable for event prediction.  The successful applicant will focus on specification and verification methods and will contribute to the realisation of tools to be adopted project-wide,and run proof-of-concepts for the technology on use cases with selected project partners. Abstraction techniques to conquer larger and more complex neural models, e.g., symbolic interval propagation methods with ReLU linearisations, are also likely to feature towards the end of the project. Familiarity with existing methods for verification of neural networks, e.g., MILP-based methods, SAT-based methods, abstraction, and optimisation is 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 and their training is highly desirable as is some experience or willingness to learn methods and tools for high-performance event-based systems.

Essential requirements:

  • Hold (or shortly expect to receive) a PhD degree in Computer Science or a related field*
  • Either a strong background in verification methods of neural networks, eg MILP-based methods, SAT-based methods, abstraction, and optimisation, or in machine learning with particular emphasis on robustness.
  • A good publication record in relevant conferences or journals.
  • Excellent oral and written communication skills as well as good social skills.
  • Ability to prioritise work to meet deadlines, and to work with minimal supervision.

*Candidates who have not yet been officially awarded their PhD will be appointed as Research Assistant within the salary range £36,694 – £39,888 per annum.

How to apply

For further details on this opportunity visit and search using vacancy reference number ENG02195, in addition to completing the online application candidate should attach. 

  • A full CV
  • Up to 1 page statement explaining what interesting issues the candidate sees in the above post and the reasons why his or her expertise is relevant.

For informal queries candidates are welcome to contact Professor Alessio Lomuscio [email protected].

For queries regarding the application process contact Jamie Perrins: [email protected]

Click Here to Apply For The Job



Please enter your comment!
Please enter your name here

Popular Jobs

Recent Comments