Research Associate in Medical AI – Internal Only

Job id: 084693. Salary: £43,205 – £44,347 per annum, including London Weighting Allowance.

Posted: 16 February 2024. Closing date: 25 February 2024.

Business unit: IoPPN. Department: Biostatistics & Health Informatics.

Contact details:Zina Ibrahim. [email protected]

Location: Denmark Hill Campus. Category: Research.

Job description
THIS VACANCY IS OPEN TO INTERNAL APPLICANTS ONLY

The postholder will have a leading role in an exciting new project for embedding knowledge in neural network architectures to derive insight from electronic health records. The successful application will investigate the multiple means for knowledge-enhanced insights including a) learning through graph neural network architectures and b) using large language models to enhance existing models. In both routes, the successful candidate will investigate the possible means of incorporating background medical knowledge, clinical guidelines and known causal pathways into advanced deep learning architectures specially designed to handle large-scale, multimodal and noisy data. 

This post will be offered on an a fixed term contract until December 2024.

This is a part-time post – 50% full time equivalent

Key responsibilities 

• Investigate different modalities of time-series data representation, including gradient-based representations and representations, e.g. Forrier transformed-data
• Implement Transformer and Deep architectures using the different data modalities to predict clinical outcomes from electronic health records data.
• Adopt a prompt-based approach to understanding the possibility of using large language models to aid existing neural architectures to enhance predictive performance using multimodal electronic health records data.         
• Communicate conceptual and complex ideas to supervisors and wider team
• To contribute actively to team meetings presenting own work, providing advice to others
• To report and disseminate methodology, results and novelty to appropriate venues (including peer-reviewed journals and conferences).

The above list of responsibilities may not be exhaustive, and the post holder will be required to undertake such tasks and responsibilities as may reasonably be expected within the scope and grading of the post.

Skills, knowledge, and experience 

Essential criteria  

An undergraduate degree in Computer Science, Engineering or a related discipline.

At least a completed postgraduate diploma in big data analytics, or either an ongoing or complete MSc in an appropriate subject (computer science, Medical Informatics, healthcare data science etc..)

Up to date knowledge of machine learning methods

Experience with neural network libraries:  Pytorch, Keras.

Fluency in Linux shell scripting and HPC script writing.

Publication record commensurate with experience

Research experience

Desirable criteria

Previous experience in data engineering, software engineering or big data analytics.

Big data technologies: Hadoop, Apache spark

Database management systems: MySQL, PostgreSQL

Research experience in Medical AI.

Further Information

We pride ourselves on being inclusive and welcoming. We embrace diversity and want everyone to feel that they belong and are connected to others in our community.

We are committed to working with our staff and unions on these and other issues, to continue to support our people and to develop a diverse and inclusive culture at King’s.

We ask all candidates to submit a copy of their CV, and a supporting statement, detailing how they meet the essential criteria listed in the advert. If we receive a strong field of candidates, we may use the desirable criteria to choose our final shortlist, so please include your evidence against these where possible.

To find out how our managers review your application, please take a look at our ‘How we Recruit’ pages.

This role does meet the requirements of the Home Office and therefore we are able to offer sponsorship for candidates who require the right to work in the UK.