About us
The UCL Bioinformatics Group is well-known for developing a widely-used suite of web-based tools based on a number of cutting edge protein structure prediction methods. Our web services have been online since 1998 and the methods available allow users to predict a variety of protein structural features, including secondary structure and natively disordered regions, protein domain boundaries and 3D models of tertiary structure.
The BBSRC funded IntegraTED project is aimed at developing a new Bioinformatics web resource hosted at UCL. Over the past 30 years the UCL Bioinformatics Group (dept of Computer Science) and the CATH Project (dept of Structural & Molecular Biology) have developed world leading web resources in structural bioinformatics. In this project we are looking to bring together three of our most important resources to develop a single, highly integrated and streamlined web platform. The aim is to provide protein structure and function researchers access to an unrivalled online research platform. The three resources involved are; the PSIPRED workbench, an online suite of machine learning based tools for analysing protein structure, The CATH-Gene3D structural classification of protein domains and The Encyclopaedia of Domains (TED) our new resource cataloguing all detectable structural domains in AlphaFoldDB.
About the role
In this project you will take the lead on the UCL Computer Science Bioinformatics Group’s portion of the IntegraTED project. There are three principle objectives in this portion of the project. In the first objective we wish to increase the reliability and performance of the existing ML workflows that underpin the PSIPRED workbench. One target here is to integrate novel bioinformatics foundation models to accelerate methods already available via the PSIPRED Workbench. The Second major objective is to work extensively on a new web interface for the IntegraTED resource. Here you will work closely with the CATH team on our planned unified web and data portal. The third major objective is to work on the TED data generation pipeline. The successful applicant for this project will work on all of these theme areas with the possibility of working on novel ML applications in this space and will importantly take the lead on developing and maintaining the PSIPRED Workbench.
This role is funded until 31st August 2029 in the first instance.
About you
The ideal applicant will be a developer with a strong interested in building Scientific Software and prior experience of software development within academia. You should have the ability and enthusiasm to acquire new skills across the ML-Ops and Bioinformatics fields. We expect good software development skills in a least one language regularly used in scientific computing (i.e. Julia, Python, etc) and you should have an interest in good practice in software development (e.g. source control, testing, etc). We focus mainly on Python but adaptability across languages is a bonus. Eventually, you will be expected to lead the development of large long standing software engineering project, so an interest in developing skill in application design is a must.
What we offer: As well as the exciting opportunities this role presents, we also offer great benefits. Please visit https://www.ucl.ac.uk/work-at-ucl/rewards-and-benefits to find out more.
Our commitment to Equality, Diversity and Inclusion: You can read more about our commitment to Equality, Diversity and Inclusion here : https://www.ucl.ac.uk/equality-diversity-inclusion/
Customer advert reference: B04-07809