Research Associate in Security of ML-based Personal Assistants

Imperial College London Department of Computing

United Kingdom

Job summary

We are seeking a talented Research Associate with a background in either machine learning, verification, or security, to be employed on the UKRI grant “Secure AI Assistants”, jointly held at King’s College London and Imperial College London. The overarching aim of the project concerns the development of various methods to show that personal AI assistants are demonstrably secure, or to identify unwanted aspects of the system so that they...

Job listing information

  • Reference ENG01292
  • Date posted 26 May 2020
  • Closing date 24 June 2020

Key information about the role

  • Location South Kensington Campus (map)
  • Position type Full time, fixed term
  • Salary £40,215 – £47,579 plus benefits
  • Department Department of Computing
  • Category Researcher / Non Clinical Researcher

Job description

Job summary

We are seeking a talented Research Associate with a background in either machine learning, verification, or security, to be employed on the UKRI grant “Secure AI Assistants”, jointly held at King’s College London and Imperial College London. The overarching aim of the project concerns the development of various methods to show that personal AI assistants are demonstrably secure, or to identify unwanted aspects of the system so that they can be rectified.

The successful applicant will focus on specification and verification methods for AI assistants based on machine-learning. This will concern 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.

The successful applicant will join the “Verification of Autonomous Systems” research group at Imperial College London, led by Professor Alessio Lomuscio, which is presently working on topics within Safe Artificial Intelligence, including but not limited to verification of autonomous systems, swarms, robustness, and safe reinforcement learning.

Duties and responsibilities

We are looking to recruit a research associate to develop novel verification methods for ML-based assistants with an emphasis on one of more of the following areas.

  • Verification and analysis of feed-forward, recurrent, LSTM and other neural networks as used in personal assistants.
  • Machine Learning with particular emphasis on robustness.
  • Tool building and engineering aspects of code analysis.

The successful candidate will work in the Verification of Autonomous Systems (VAS) research group, a vibrant, multi-national team working on various aspects of safe Artificial Intelligence, including verification and safety aspects of machine learning systems, autonomous systems, swarm-based systems, logic-based verification, probabilistic model checking and safe reinforcement learning.

The VAS group also contributes to US funded projects on Assured Autonomy and has strong links with the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence. The Department of Computing at Imperial College London is a leading department of Computer Science in the UK.

Essential requirements

    • To hold (or shortly expect to receive) a PhD degree in Computer Science or a related field *
    • Applicants are expected to have either of the following:

        • A strong background in either formal verification, SMT solving, optimisation, or security.

        • A strong background in machine learning with particular emphasis to either verification or robustness.
    • Proven knowledge and track record in one or more of the following areas:

        • Deep learning

        • Security

        • Verification

        • Optimisation.
    • A strong publication track record in relevant conferences or journals.
    • Excellent oral, written communication skills as well as social skills.
    • Able to organise your work with minimal supervision and prioritise work to meet deadlines.

Good communication, excellent technical writing skills, and an ability to prioritise work to meet deadlines is essential. A proven ability to program and maintain state-of-the-art toolkits is highly desirable.

Further information

Candidates who have not yet been officially awarded their PhD will be appointed as Research Assistant within the salary range £35,477 - £38,566 per annum.

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 a.lomuscio@imperial.ac.uk. 

For queries regarding the application process contact Jamie Perrins: j.perrins@imperial.ac.uk

For technical issues when applying online please emailrecruitment@imperial.ac.uk

Committed to equality and valuing diversity, we are an Athena SWAN Silver Award winner, a Stonewall Diversity Champion, a Disability Confident Employer and work in partnership with GIRES to promote respect for trans people.

The College is a proud signatory to the San-Francisco Declaration on Research Assessment (DORA),which means that in hiring and promotion decisions, we evaluate applicants on the quality of their work, not the journal impact factor where it is published. For more information, see https://www.imperial.ac.uk/research-and-innovation/about-imperial-research/research-evaluation/

The College believes that the use of animals in research is vital to improve human and animal health and welfare. Animals may only be used in research programmes where their use is shown to be necessary for developing new treatments and making medical advances. Imperial is committed to ensuring that, in cases where this research is deemed essential, all animals in the College’s care are treated with full respect, and that all staff involved with this work show due consideration at every level.http://www.imperial.ac.uk/research-and-innovation/about-imperial-research/research-integrity/animal-research/ 


In your application, please refer to Polytechnicpositions.com

FACEBOOK
TWITTER
LINKEDIN

baner1

baner10

baner11

baner12

baner14

baner2

baner3

baner4

baner5

baner6

baner8

baner9